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

    Neuronpedia

    INDEX
    Explanations

    words related to user commands or actions in programming contexts

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

    ajedrez

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oa̍t
    -0.55
     tartalomajánló
    -0.51
    Abitanti
    -0.51
    __(/*!
    -0.50
    awtextra
    -0.45
     surla
    -0.42
    __":
    -0.41
     AttributeSet
    -0.41
     lutter
    -0.40
    printStackTrace
    -0.40
    POSITIVE LOGITS
    AnchorStyles
    0.45
     înd
    0.45
     down
    0.43
     hemsida
    0.42
     transférez
    0.41
    cur
    0.41
     CURIAM
    0.40
    zzá
    0.39
    TableId
    0.39
     fidélité
    0.39
    Act Density 0.019%

    No Known Activations