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

    Neuronpedia

    INDEX
    Explanations

    calculus home links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    label
    0.42
    pass
    0.42
    which
    0.42
    who
    0.41
    etsch
    0.40
    ifen
    0.40
    secondary
    0.40
    System
    0.39
    Image
    0.39
    Mars
    0.39
    POSITIVE LOGITS
     derivadas
    0.47
     baddies
    0.43
    uración
    0.41
     அன்று
    0.41
     الدراسي
    0.41
     instalado
    0.41
     refor
    0.41
     derivados
    0.40
     triángulos
    0.40
     deriv
    0.40
    Act Density 0.002%

    No Known Activations