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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ца
    -0.08
    cip
    -0.07
    .assertEqual
    -0.07
     узнать
    -0.07
    不死
    -0.07
     Principal
    -0.06
    땧
    -0.06
    _One
    -0.06
    Տ
    -0.06
     Replica
    -0.06
    POSITIVE LOGITS
     MMM
    0.08
     arab
    0.07
    持有人
    0.07
     hairstyles
    0.07
    gambar
    0.06
    ("\"
    0.06
    咩
    0.06
    olidays
    0.06
    咯
    0.06
    -popup
    0.06
    Act Density 0.001%

    No Known Activations