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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chod
    -0.07
    uyên
    -0.06
     Tr
    -0.06
    Calculate
    -0.06
    .predict
    -0.06
     scooter
    -0.06
    .Bl
    -0.06
    Viewer
    -0.06
    .RowStyle
    -0.06
    :ss
    -0.06
    POSITIVE LOGITS
     Affero
    0.07
     interested
    0.07
     Üç
    0.06
    jectives
    0.06
     Morales
    0.06
     savage
    0.06
     Chỉ
    0.06
     suffix
    0.06
     месте
    0.06
    辅
    0.06
    Act Density 0.001%

    No Known Activations