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

    Neuronpedia

    INDEX
    Explanations

    the word "not"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     won
    -0.48
    Fall
    -0.45
    dirname
    -0.45
    won
    -0.45
    题
    -0.44
     properly
    -0.44
    timestamps
    -0.44
    Won
    -0.43
    NVIC
    -0.43
     Won
    -0.43
    POSITIVE LOGITS
     protoimpl
    0.75
     verwe
    0.66
    NUMX
    0.61
    ArrowToggle
    0.60
    EndContext
    0.60
    المناصب
    0.60
    urlpatterns
    0.60
    ьаж
    0.59
     GenerationType
    0.59
    StoreMessageInfo
    0.58
    Act Density 0.076%

    No Known Activations