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

    Neuronpedia

    INDEX
    Explanations

    Research citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     argument
    -0.07
    .ReadAsStringAsync
    -0.07
     dummy
    -0.06
    (sym
    -0.06
    sar
    -0.06
     redirection
    -0.06
    (animated
    -0.06
     powerful
    -0.06
    まま
    -0.06
    _writer
    -0.06
    POSITIVE LOGITS
    ruk
    0.08
    -touch
    0.07
    touch
    0.07
    iores
    0.07
    🥣
    0.07
    ンド
    0.06
    电信
    0.06
    ציות
    0.06
    تق
    0.06
     Explorer
    0.06
    Act Density 0.018%

    No Known Activations