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

    Neuronpedia

    INDEX
    Explanations

    elements of computer code related to user interface and interaction

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

    Code and special characters

    np_acts-logits-general · gemini-2.0-flash

    few around cause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iddhar
    -0.70
    外部リンク
    -0.70
    ؤلاء
    -0.67
    windowFixed
    -0.65
    |}{$
    -0.64
    >--}}
    -0.63
     createStore
    -0.63
    UniformLocation
    -0.63
     GenerationType
    -0.63
     ProtoMessage
    -0.61
    POSITIVE LOGITS
    󠁿
    0.78
    0.74
    [toxicity=0]
    0.68
    enumi
    0.67
    s
    0.60
     متعلقه
    0.60
    er
    0.58
    o
    0.57
    ں
    0.57
    hline
    0.54
    Act Density 0.026%
    No Known Activations