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

    Neuronpedia

    INDEX
    Explanations

    numbers or list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Prison
    0.41
    Optical
    0.38
     Embedded
    0.38
    plectic
    0.37
    W
    0.36
    Lunar
    0.36
     Lunar
    0.36
    S
    0.36
     Aqueous
    0.35
     Uniform
    0.34
    POSITIVE LOGITS
    を務
    0.42
     returning
    0.41
     pintar
    0.41
    पेड
    0.40
    returning
    0.40
     orchestr
    0.40
     jornalista
    0.40
     खरीदने
    0.39
     utilisons
    0.39
     популярных
    0.39
    Act Density 0.000%

    No Known Activations