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

    Neuronpedia

    INDEX
    Explanations

    os

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    五百
    -0.08
    -0.07
    融创
    -0.07
    ="./
    -0.07
    之初
    -0.07
     vast
    -0.07
    乘
    -0.07
     tu
    -0.07
     captain
    -0.07
    周三
    -0.06
    POSITIVE LOGITS
    .toUpperCase
    0.07
    ки
    0.07
     loadImage
    0.07
    amanho
    0.07
     rainbow
    0.07
    🥑
    0.07
    _Parms
    0.07
     tract
    0.07
    前不久
    0.07
    jabi
    0.07
    Act Density 0.005%

    No Known Activations