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

    Neuronpedia

    INDEX
    Explanations

    anger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    できます
    -0.07
    selector
    -0.07
     eclectic
    -0.07
    ------+
    -0.07
    adık
    -0.06
    lıyor
    -0.06
     doldur
    -0.06
    办法
    -0.06
    WATCH
    -0.06
    CHAIN
    -0.06
    POSITIVE LOGITS
    723
    0.07
    710
    0.07
    зація
    0.07
     upset
    0.07
     Correct
    0.07
    _ce
    0.07
     Nowadays
    0.06
    _Vector
    0.06
     unexpected
    0.06
    ylie
    0.06
    Act Density 0.016%

    No Known Activations