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

    Neuronpedia

    INDEX
    Explanations

    specific numeric data and references in scientific contexts

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

    Text within brackets or parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.73
     in
    -0.59
     a
    -0.59
     
    -0.56
     for
    -0.56
     on
    -0.56
     and
    -0.54
     as
    -0.52
     the
    -0.52
     sur
    -0.51
    POSITIVE LOGITS
     مشين
    1.12
     CreateTagHelper
    1.10
     kasarigan
    1.08
    enderror
    0.99
    ynchronously
    0.96
     تانيه
    0.95
     myſelf
    0.94
     الحره
    0.94
     Efq
    0.94
    extAlignment
    0.93
    Act Density 0.783%

    No Known Activations