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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     який
    -0.07
    缘
    -0.07
    DDS
    -0.06
    bairro
    -0.06
    بود
    -0.06
     MONEY
    -0.06
    ूसर
    -0.06
    溶
    -0.06
     czas
    -0.06
    .Millisecond
    -0.06
    POSITIVE LOGITS
    .child
    0.07
    onth
    0.07
     Special
    0.07
    Michael
    0.06
    _z
    0.06
    192
    0.06
     Mock
    0.06
     titleLabel
    0.06
    anch
    0.06
     Global
    0.06
    Act Density 0.001%

    No Known Activations