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

    Neuronpedia

    INDEX
    Explanations

    prevention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tree
    -0.08
    =M
    -0.07
     Monter
    -0.07
    Dic
    -0.06
     Drinking
    -0.06
    енные
    -0.06
    opes
    -0.06
     spelling
    -0.06
     drilling
    -0.06
    桑
    -0.06
    POSITIVE LOGITS
     assumptions
    0.07
    _EMAIL
    0.07
     зал
    0.06
    وب
    0.06
    forman
    0.06
     baja
    0.06
    ząd
    0.06
    maması
    0.06
    asında
    0.06
    ерами
    0.06
    Act Density 0.014%

    No Known Activations