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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ears
    -0.07
     Beispiel
    -0.07
     anni
    -0.07
    +"'
    -0.07
     번째
    -0.07
     bowling
    -0.06
    :path
    -0.06
    /editor
    -0.06
    +")
    -0.06
    пион
    -0.06
    POSITIVE LOGITS
     ########################
    0.07
    /************************
    0.07
     experimenting
    0.07
    _pickle
    0.06
     kazan
    0.06
    승
    0.06
     Plzeň
    0.06
    昇
    0.06
    леч
    0.06
    晓
    0.06
    Act Density 0.075%

    No Known Activations