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

    Neuronpedia

    INDEX
    Explanations

    references to differences and variation among subjects or conditions

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

    specifying contexts for qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     macchina
    -0.34
     bocca
    -0.30
    saraba
    -0.29
     parent
    -0.28
    pages
    -0.28
     central
    -0.28
     cottura
    -0.27
     Black
    -0.27
     cabinet
    -0.27
     spin
    -0.26
    POSITIVE LOGITS
    IntoConstraints
    0.71
    点此举报
    0.66
     Lightboxes
    0.65
    xase
    0.65
     gynhyrchwyd
    0.64
     nahilalakip
    0.64
    InjectAttribute
    0.61
     урна
    0.59
    TypedDataSet
    0.57
     JpaRepository
    0.57
    Act Density 0.512%

    No Known Activations