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

    Neuronpedia

    INDEX
    Explanations

    references to legal terms and institutions

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

    Expressing gratitude or appreciation

    np_acts-logits-general · gemini-2.0-flash

    acknowledging contributions and thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     /\.
    -0.70
    ⓧ
    -0.67
    :✨
    -0.66
    ineno
    -0.65
    Cyfeiriadau
    -0.62
     supposedly
    -0.61
     onView
    -0.61
    ))[
    -0.60
    principalTable
    -0.60
    WithIOException
    -0.60
    POSITIVE LOGITS
    のおかげ
    0.70
     graciously
    0.70
     generous
    0.70
     generosity
    0.69
     generously
    0.69
     kindly
    0.63
     wonderful
    0.63
     invaluable
    0.61
     contributed
    0.60
    おかげ
    0.60
    Act Density 0.181%

    No Known Activations