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

    Neuronpedia

    INDEX
    Explanations

    held

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Filipino
    -0.07
     ún
    -0.07
     Karel
    -0.07
    _encoded
    -0.06
    ��
    -0.06
    âce
    -0.06
     Fraser
    -0.06
    @m
    -0.06
    odigo
    -0.06
     beer
    -0.06
    POSITIVE LOGITS
     glor
    0.07
    ेकर
    0.07
    ITIONS
    0.06
    هوری
    0.06
    잔
    0.06
     Seminar
    0.06
    .Requires
    0.06
     preliminary
    0.06
     sicher
    0.06
     метод
    0.06
    Act Density 0.012%

    No Known Activations