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

    Neuronpedia

    INDEX
    Explanations

    certainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     habitual
    -0.06
    찬
    -0.06
     switching
    -0.06
    .xaxis
    -0.06
    .spinner
    -0.06
    Browsable
    -0.06
    这种
    -0.06
     आस
    -0.06
    pp
    -0.06
    つぶ
    -0.06
    POSITIVE LOGITS
     امروز
    0.07
    _ADMIN
    0.07
     SCI
    0.06
     Орг
    0.06
     autoplay
    0.06
     dib
    0.06
    าชน
    0.06
     Every
    0.06
    Sci
    0.06
    .Link
    0.06
    Act Density 0.089%

    No Known Activations