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

    Neuronpedia

    INDEX
    Explanations

    Appeal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parties
    -0.07
     rud
    -0.07
     گاه
    -0.07
     Blonde
    -0.07
    组
    -0.06
    asctime
    -0.06
     Deer
    -0.06
     нам
    -0.06
     sou
    -0.06
    	req
    -0.06
    POSITIVE LOGITS
     saturated
    0.07
    cip
    0.07
    Tensor
    0.06
    _entropy
    0.06
    .Light
    0.06
     ASTM
    0.06
     Garmin
    0.06
    |max
    0.06
     multinational
    0.06
    �습니다
    0.06
    Act Density 0.001%

    No Known Activations