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

    Neuronpedia

    INDEX
    Explanations

    business descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coke
    -0.07
    _income
    -0.06
    .Client
    -0.06
    .likes
    -0.06
    ยะ
    -0.06
    Sau
    -0.06
    iPhone
    -0.06
     домашних
    -0.06
    zag
    -0.06
     American
    -0.06
    POSITIVE LOGITS
     odpowied
    0.07
     міг
    0.06
     адже
    0.06
     Purpose
    0.06
     کود
    0.06
     대부분
    0.06
     连
    0.06
     सफ
    0.06
     Beh
    0.06
     seper
    0.06
    Act Density 0.058%

    No Known Activations