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

    Neuronpedia

    INDEX
    Explanations

    describing qualities or specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.55
    z
    0.55
    x
    0.54
    b
    0.50
    ch
    0.50
    /
    0.50
    h
    0.49
    Sub
    0.49
    q
    0.49
    CM
    0.48
    POSITIVE LOGITS
     proporciona
    0.66
     oferece
    0.66
     menerima
    0.64
     textarea
    0.64
     consente
    0.63
     userRoutes
    0.61
     aiuta
    0.60
     molte
    0.59
     ajuda
    0.59
     ofrece
    0.58
    Act Density 0.000%

    No Known Activations