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

    Neuronpedia

    INDEX
    Explanations

    98

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clown
    -0.07
     FIRE
    -0.07
     právě
    -0.07
    logue
    -0.06
    是不
    -0.06
     tzv
    -0.06
    -prop
    -0.06
     látky
    -0.06
     jmen
    -0.06
    cü
    -0.06
    POSITIVE LOGITS
     prompt
    0.06
    75
    0.06
    .userData
    0.06
     sexuales
    0.06
    ятся
    0.06
    ugador
    0.06
    qq
    0.06
     Bris
    0.06
    =S
    0.06
    .check
    0.06
    Act Density 0.013%

    No Known Activations