Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication effectiveness and the need for clarity in messaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding a conjunction or punctuation

    np_acts-logits-general · gemini-2.0-flash

    leader, careful, offense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vogel
    -0.45
     bears
    -0.42
     Malcolm
    -0.42
     Geschw
    -0.40
     organizational
    -0.40
     bear
    -0.40
    Malcolm
    -0.40
    organizational
    -0.38
    ByUsername
    -0.37
     Lebe
    -0.37
    POSITIVE LOGITS
    ंदीखरीदारी
    0.59
    RenderAtEndOf
    0.55
     HttpNotFound
    0.55
     ModelExpression
    0.54
    RegressionTest
    0.54
    Datuak
    0.53
    ContentAsync
    0.52
    ViewImports
    0.51
    SharedDtor
    0.50
    hasMoreElements
    0.49
    Act Density 0.608%

    No Known Activations