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

    Neuronpedia

    INDEX
    Explanations

    cells

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    keeping
    -0.07
     propensity
    -0.07
    楽し
    -0.07
    (
    -0.07
     spontaneously
    -0.06
     לחלוטין
    -0.06
     marginal
    -0.06
    淞
    -0.06
    topl
    -0.06
    浣
    -0.06
    POSITIVE LOGITS
    caffe
    0.07
     retir
    0.06
     gy
    0.06
    ERY
    0.06
     vw
    0.06
    يو
    0.06
     unfit
    0.06
    Dto
    0.06
     uncle
    0.06
    GI
    0.06
    Act Density 0.041%

    No Known Activations