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

    Neuronpedia

    INDEX
    Explanations

    Anticipating a better outcome

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stage
    -0.07
     الغ
    -0.07
     stage
    -0.07
    ://%
    -0.06
    ='"+
    -0.06
     セ
    -0.06
    Radio
    -0.06
     �
    -0.06
     strives
    -0.06
    VERY
    -0.06
    POSITIVE LOGITS
    ‌شوند
    0.07
     humano
    0.07
     Determines
    0.06
     survives
    0.06
     vendor
    0.06
    _pwd
    0.06
    >#
    0.06
     svob
    0.06
    _removed
    0.06
    وجه
    0.06
    Act Density 0.060%

    No Known Activations