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

    Neuronpedia

    INDEX
    Explanations

    complex topic or process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nuovi
    0.63
    നിക്ക
    0.61
    ًا
    0.57
     desplazamiento
    0.57
     rozwiązania
    0.57
     Lösungen
    0.57
     eller
    0.57
     versiones
    0.55
     druk
    0.55
     sih
    0.55
    POSITIVE LOGITS
     phénomène
    0.72
     affair
    0.67
     phenomenon
    0.66
    Doing
    0.66
     AFFA
    0.66
     गोष्ट
    0.63
     Affair
    0.61
     feat
    0.60
     기능
    0.59
    하고
    0.58
    Act Density 0.430%

    No Known Activations