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

    Neuronpedia

    INDEX
    Explanations

    US role in world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Công
    -0.07
     baik
    -0.07
    usters
    -0.06
    CEEDED
    -0.06
    ADF
    -0.06
    Inc
    -0.06
     Blade
    -0.06
     CEO
    -0.06
     Crud
    -0.06
     başlar
    -0.06
    POSITIVE LOGITS
    _recommend
    0.07
     Bols
    0.07
     intrusive
    0.06
    .widgets
    0.06
     cure
    0.06
    _symbols
    0.06
    contract
    0.06
    .identifier
    0.06
    ุปกรณ
    0.06
    ��索
    0.06
    Act Density 0.108%

    No Known Activations