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

    Neuronpedia

    INDEX
    Explanations

    numerical values that signify quantities, time, or statistics

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

    years

    np_acts-logits-general · gemini-2.0-flash

    years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.78
     autorytatywna
    -0.74
     WaitForSeconds
    -0.71
    ResumeLayout
    -0.70
     nahilalakip
    -0.70
    ]';
    -0.69
    InjectAttribute
    -0.69
     estekak
    -0.68
     DbType
    -0.65
    rdı
    -0.65
    POSITIVE LOGITS
    0
    1.12
    8
    0.65
    7
    0.61
    4
    0.61
     ۲۰۰
    0.60
    5
    0.60
    6
    0.59
    2
    0.58
    눠
    0.56
    3
    0.56
    Act Density 0.090%

    No Known Activations