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

    Neuronpedia

    INDEX
    Explanations

    programming languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Anthem
    -1.00
    Produced
    -0.77
     sanitaires
    -0.72
     jargon
    -0.68
     juridiques
    -0.67
     anthem
    -0.66
     مشين
    -0.66
     supérieurs
    -0.66
    ArgsConstructor
    -0.65
     médicaux
    -0.65
    POSITIVE LOGITS
    apl
    0.52
     للمعارف
    0.50
    QUICK
    0.50
    neté
    0.50
    новниш
    0.49
     CanadaChoose
    0.49
    لاق
    0.49
    ISK
    0.48
    Откры
    0.48
    ayam
    0.47
    Act Density 1.522%

    No Known Activations