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

    Neuronpedia

    INDEX
    Explanations

    coach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     усл
    -0.06
     draggable
    -0.06
    소개
    -0.06
     zemí
    -0.06
    賣
    -0.06
    Multiply
    -0.06
    _nv
    -0.06
    separator
    -0.06
     응
    -0.06
    -0.06
    POSITIVE LOGITS
     intra
    0.08
     در
    0.07
    wd
    0.07
     mildly
    0.07
     prin
    0.07
    HeadersHeightSizeMode
    0.07
     wei
    0.07
     Floral
    0.06
     */,↵
    0.06
    !:
    0.06
    Act Density 0.009%

    No Known Activations