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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obsessive
    -0.07
    .Params
    -0.07
    vider
    -0.06
    asso
    -0.06
    hurst
    -0.06
    tod
    -0.06
    es
    -0.06
    sein
    -0.06
    _-
    -0.06
    _python
    -0.06
    POSITIVE LOGITS
     which
    0.10
     lowercase
    0.09
    which
    0.08
     مما
    0.07
    ıyordu
    0.07
    /compiler
    0.06
     nếu
    0.06
     terrific
    0.06
     butterflies
    0.06
     WHICH
    0.06
    Act Density 0.079%

    No Known Activations