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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voiture
    -0.06
     زی
    -0.06
    دث
    -0.06
    PB
    -0.06
    Li
    -0.06
    这一
    -0.06
    児
    -0.06
    dar
    -0.05
    ้แก
    -0.05
    truck
    -0.05
    POSITIVE LOGITS
     Penalty
    0.06
     cholesterol
    0.06
     nomination
    0.06
    UDP
    0.06
    Regions
    0.06
     مصرف
    0.06
    _hierarchy
    0.06
     salt
    0.06
     edition
    0.06
    _EQUAL
    0.06
    Act Density 0.000%

    No Known Activations