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

    Neuronpedia

    INDEX
    Explanations

    tried to speak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vist
    0.46
    äh
    0.45
    eten
    0.44
     comparte
    0.44
    ב
    0.44
     vanno
    0.43
     godt
    0.43
     seren
    0.43
    بيض
    0.43
     sest
    0.43
    POSITIVE LOGITS
     Kesehatan
    0.48
     உருவாக
    0.46
     መሳሪያ
    0.45
    DX
    0.44
     Umgang
    0.41
    夰
    0.41
     स्वस्थ
    0.41
     علاج
    0.41
     гидро
    0.41
    radiative
    0.41
    Act Density 0.010%

    No Known Activations