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

    Neuronpedia

    INDEX
    Explanations

    academic references and citations

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

    Citations inside square brackets

    np_acts-logits-general · gemini-2.0-flash

    in-text citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.51
     utafitiHapana
    -0.42
    ShouldBe
    -0.39
     démocr
    -0.38
     APM
    -0.36
    IntoConstraints
    -0.35
     évidemment
    -0.34
     gerekiyor
    -0.34
     voulons
    -0.34
    TextBoxColumn
    -0.34
    POSITIVE LOGITS
    suggested
    0.52
     suggested
    0.51
     reported
    0.50
     proposing
    0.49
    AndEndTag
    0.49
    ictwo
    0.48
    followers
    0.45
     Lordships
    0.44
     dimaksud
    0.44
    epar
    0.44
    Act Density 2.219%

    No Known Activations