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

    Neuronpedia

    INDEX
    Explanations

    price, original, effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    étais
    0.86
    鉐
    0.82
    onica
    0.80
    belle
    0.76
    caria
    0.76
    heiten
    0.75
     Faces
    0.74
    ধবার
    0.73
     Щ
    0.73
    ≦
    0.73
    POSITIVE LOGITS
     defenders
    0.74
    ండి
    0.74
    एमपी
    0.71
     comidas
    0.68
     coils
    0.66
    යේ
    0.66
    ıdır
    0.66
    uctive
    0.66
     sederhana
    0.65
    NotEmpty
    0.64
    Act Density 0.000%

    No Known Activations