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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prene
    -0.07
    이라는
    -0.07
    Bitte
    -0.06
     　 　 　 　 　 　
    -0.06
    であった
    -0.06
     collapse
    -0.06
    Cancelar
    -0.06
    →→
    -0.06
    　 　 　 　 　 　
    -0.06
    etiyle
    -0.06
    POSITIVE LOGITS
     cherry
    0.07
    .shape
    0.07
    rection
    0.07
     whole
    0.06
    (words
    0.06
    eguard
    0.06
     SOP
    0.06
     جن
    0.06
    向
    0.06
     MOVE
    0.06
    Act Density 0.002%

    No Known Activations