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

    Neuronpedia

    INDEX
    Explanations

    film descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sic
    -0.06
     iss
    -0.06
     Powers
    -0.06
     �
    -0.06
     insulting
    -0.06
     thiệu
    -0.06
     Psychology
    -0.06
     dise
    -0.06
    िड
    -0.06
    )initWith
    -0.06
    POSITIVE LOGITS
    	wait
    0.07
    adds
    0.07
    .Weight
    0.07
    499
    0.07
     бл
    0.07
     до
    0.06
    омен
    0.06
    距離
    0.06
     mascara
    0.06
    |RF
    0.06
    Act Density 0.000%

    No Known Activations