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

    Neuronpedia

    INDEX
    Explanations

    data or statistical references in research contexts

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

    Numbers inside square brackets

    np_acts-logits-general · gemini-2.0-flash

    log *k* or *P*="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     typelib
    -1.05
     Мексичка
    -0.96
     Vikipedi
    -0.94
     unknownFields
    -0.91
    GraphicsUnit
    -0.86
     الرياضيه
    -0.85
     незавершена
    -0.76
    tonode
    -0.76
    archiviato
    -0.74
     Савезне
    -0.74
    POSITIVE LOGITS
    c
    0.68
    b
    0.64
     socialization
    0.63
     ayr
    0.56
    3
    0.55
    _
    0.53
    la
    0.53
    g
    0.53
    r
    0.53
    格
    0.52
    Act Density 0.771%

    No Known Activations