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

    Neuronpedia

    INDEX
    Explanations

    russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conforme
    -0.07
    _period
    -0.07
    _NUM
    -0.06
    .Component
    -0.06
    过了
    -0.06
    @pytest
    -0.06
     continent
    -0.06
     contacting
    -0.06
    .length
    -0.06
    ϰ
    -0.06
    POSITIVE LOGITS
    Thumb
    0.07
    充当
    0.07
    任教
    0.07
    ig
    0.07
    <path
    0.07
    钱币
    0.07
    (lbl
    0.07
    anyahu
    0.07
    醒目
    0.07
     adds
    0.07
    Act Density 0.281%

    No Known Activations