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

    Neuronpedia

    INDEX
    Explanations

    ogeneity partially

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     거
    -0.07
    ôme
    -0.07
    来自于
    -0.07
    ﾞ
    -0.07
    "That
    -0.06
    🅚
    -0.06
     following
    -0.06
     proof
    -0.06
    Tİ
    -0.06
     actor
    -0.06
    POSITIVE LOGITS
    腊
    0.08
     compounded
    0.07
    _IMP
    0.07
     tsunami
    0.07
    疲劳
    0.07
    .sp
    0.07
    _stock
    0.07
     FileStream
    0.07
    躺
    0.07
     HEALTH
    0.07
    Act Density 0.112%

    No Known Activations