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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    礼
    -0.08
    禮
    -0.07
    cache
    -0.07
     �
    -0.06
    不存在
    -0.06
    แน
    -0.06
     powdered
    -0.06
    ของค
    -0.06
    malar
    -0.06
    arse
    -0.06
    POSITIVE LOGITS
    _Call
    0.07
     Yankees
    0.06
     분
    0.06
    _INTR
    0.06
    PointerType
    0.06
     qued
    0.06
    ections
    0.06
     institute
    0.06
    .parseFloat
    0.06
    _free
    0.06
    Act Density 0.100%

    No Known Activations