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

    Neuronpedia

    INDEX
    Explanations

    legal restrictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ASSE
    1.02
     Cert
    0.79
    ായ്
    0.79
     Кан
    0.77
    А
    0.77
    戙
    0.77
    реди
    0.76
    มอบ
    0.75
    Само
    0.74
    ک
    0.74
    POSITIVE LOGITS
     enactment
    0.89
     prohibiting
    0.89
    ור
    0.86
    ə
    0.82
     enacted
    0.77
     enforcement
    0.77
     extant
    0.75
     noin
    0.75
     prohibitions
    0.74
     laws
    0.73
    Act Density 0.373%

    No Known Activations