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

    Neuronpedia

    INDEX
    Explanations

    pay/for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     input
    -0.06
     sleeper
    -0.06
    ับค
    -0.06
    .Port
    -0.06
     LSTM
    -0.06
     Deprecated
    -0.06
     серед
    -0.06
    请求
    -0.06
    .um
    -0.06
     shipment
    -0.06
    POSITIVE LOGITS
    ♠
    0.08
    ethnic
    0.07
     تصویر
    0.07
    ...
    0.06
    sports
    0.06
     Added
    0.06
     locked
    0.06
     Glyph
    0.06
     danger
    0.06
    stricted
    0.06
    Act Density 0.017%

    No Known Activations