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

    Neuronpedia

    INDEX
    Explanations

    selector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Business
    -0.07
     celebrated
    -0.07
    Thu
    -0.07
     mar
    -0.07
     beauty
    -0.06
     fragment
    -0.06
     Cake
    -0.06
    .getRandom
    -0.06
     Αρχ
    -0.06
     Friday
    -0.06
    POSITIVE LOGITS
    essa
    0.07
    ULT
    0.07
     Hội
    0.06
    TOR
    0.06
     Ult
    0.06
    โซ
    0.06
    ความ
    0.06
     ノ
    0.06
    _ref
    0.06
     UEFA
    0.06
    Act Density 0.002%

    No Known Activations