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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	gbc
    -0.07
     submits
    -0.07
     scored
    -0.07
    ，如果
    -0.06
     adc
    -0.06
    Pokud
    -0.06
    ahir
    -0.06
    uml
    -0.06
     etmek
    -0.06
    ií
    -0.06
    POSITIVE LOGITS
     настоя
    0.07
    女人
    0.07
     similarities
    0.06
    "{
    0.06
     tener
    0.06
    촌
    0.06
     Calcul
    0.06
    device
    0.06
    _appro
    0.06
    ",'
    0.06
    Act Density 0.037%

    No Known Activations