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

    Neuronpedia

    INDEX
    Explanations

    exaggeration of positive qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ppm
    0.92
    endre
    0.89
    ของคุณ
    0.84
    hem
    0.83
     MB
    0.83
     SMART
    0.83
    APP
    0.83
    mes
    0.83
    층
    0.83
    dys
    0.82
    POSITIVE LOGITS
     revêtu
    1.12
     nešto
    1.11
    த்தொ
    1.10
     આજ
    1.06
     اہمیت
    1.06
     grabación
    1.04
    Electricity
    1.03
     rozpoczę
    1.03
    ząt
    1.02
     sesuatu
    1.02
    Act Density 0.102%

    No Known Activations