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

    Neuronpedia

    INDEX
    Explanations

    punctuations or sentence-ending symbols

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

    Punctuation followed by an introductory word

    np_acts-logits-general · gemini-2.0-flash

    process descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.72
    .
    -0.64
     they
    -0.58
     the
    -0.58
     people
    -0.56
     we
    -0.55
    ыре
    -0.53
     People
    -0.52
    ,
    -0.52
     The
    -0.51
    POSITIVE LOGITS
     Needless
    1.05
     itſelf
    1.01
    Needless
    1.01
    withstanding
    1.00
    Примеча
    0.98
     fubject
    0.98
     Accordingly
    0.97
     juſt
    0.95
    ſelves
    0.92
     ſind
    0.91
    Act Density 0.438%

    No Known Activations