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

    Neuronpedia

    INDEX
    Explanations

    DIY crafts and recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dim
    -0.07
     NATIONAL
    -0.07
     zf
    -0.06
    かり
    -0.06
     STATE
    -0.06
    TIME
    -0.06
    .Run
    -0.06
    _break
    -0.06
    reader
    -0.06
     usleep
    -0.06
    POSITIVE LOGITS
     вуз
    0.07
     foss
    0.06
     розвитку
    0.06
     Тому
    0.06
     Mann
    0.06
    ahrungen
    0.06
    llum
    0.06
    ावन
    0.06
    untu
    0.06
     forts
    0.06
    Act Density 0.019%

    No Known Activations