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

    Neuronpedia

    INDEX
    Explanations

    json-like structure elements or syntax

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

    Tokens before square brackets

    np_acts-logits-general · gemini-2.0-flash

    structured text punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.92
    ↵↵
    -0.79
    !
    -0.64
    ?
    -0.61
    ↵↵↵
    -0.59
    ,
    -0.58
    ↵↵↵↵
    -0.56
    .</
    -0.54
    .
    -0.52
    .
    -0.50
    POSITIVE LOGITS
     للمعارف
    1.16
    MigrationBuilder
    1.11
    UnknownFieldSet
    0.93
     الحره
    0.85
    Autoritní
    0.85
    AddTagHelper
    0.84
    tagHelperRunner
    0.81
     myſelf
    0.79
    出版年
    0.78
    errHandler
    0.77
    Act Density 0.279%

    No Known Activations