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

    Neuronpedia

    INDEX
    Explanations

    rate on a scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ह
    0.83
    ור
    0.82
    ammo
    0.82
    ни
    0.78
    asse
    0.73
    น
    0.72
    र्
    0.72
    но
    0.71
    ENABLE
    0.68
    ANN
    0.67
    POSITIVE LOGITS
     использу
    0.95
     utilizados
    0.94
     använder
    0.93
     použí
    0.91
    ழ்க
    0.90
     utilizando
    0.88
     lineales
    0.87
     použív
    0.87
     öğret
    0.86
     símbolos
    0.86
    Act Density 0.008%

    No Known Activations