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

    Neuronpedia

    INDEX
    Explanations

    what would questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arbeitet
    0.88
     që
    0.84
    évő
    0.83
     こと
    0.83
     gì
    0.82
     vais
    0.82
     cleft
    0.82
    ҥ
    0.82
    Believe
    0.81
     sendiri
    0.81
    POSITIVE LOGITS
     be
    0.92
     their
    0.90
     convincing
    0.87
    their
    0.83
     motivating
    0.81
     our
    0.79
    top
    0.77
     persuading
    0.74
     realistic
    0.73
     Their
    0.72
    Act Density 0.034%

    No Known Activations