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

    Neuronpedia

    INDEX
    Explanations

    lose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    잖
    -0.08
    Date
    -0.07
    .#
    -0.07
     Click
    -0.06
    くれた
    -0.06
    ерб
    -0.06
     exploding
    -0.06
    กราคม
    -0.06
    lendirme
    -0.06
     нем
    -0.06
    POSITIVE LOGITS
    /vue
    0.06
    formation
    0.06
    .getTime
    0.06
    !I
    0.06
    label
    0.06
    rq
    0.06
     splitter
    0.06
    ?</
    0.06
    /ge
    0.06
    _makeConstraints
    0.06
    Act Density 0.011%

    No Known Activations