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

    Neuronpedia

    INDEX
    Explanations

    fond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifié
    -0.07
    cesso
    -0.07
    扫码
    -0.07
    explo
    -0.07
    änger
    -0.06
     suck
    -0.06
    airo
    -0.06
    迴
    -0.06
     approaching
    -0.06
    .ValidationError
    -0.06
    POSITIVE LOGITS
    Et
    0.07
    STIT
    0.07
     Mat
    0.07
    _DS
    0.07
     prostit
    0.07
    ・
    0.06
    _deep
    0.06
    The
    0.06
    幖
    0.06
    تس
    0.06
    Act Density 0.002%

    No Known Activations