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

    Neuronpedia

    INDEX
    Explanations

    polar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    釋
    -0.07
    .Nullable
    -0.07
    清醒
    -0.07
    أسباب
    -0.07
    CMP
    -0.07
     reasoned
    -0.06
     SPA
    -0.06
     sæ
    -0.06
    謝
    -0.06
    肌
    -0.06
    POSITIVE LOGITS
    sprites
    0.07
    .getHeader
    0.07
    ICTURE
    0.07
     Memorial
    0.07
    _UTIL
    0.07
    альных
    0.07
     loadImage
    0.07
    actical
    0.07
    𝓰
    0.07
    [index
    0.06
    Act Density 0.002%

    No Known Activations