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

    Neuronpedia

    INDEX
    Explanations

    say "for"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     začal
    -0.06
     Wet
    -0.06
    пов
    -0.06
     PCs
    -0.06
    _df
    -0.06
     Adaptive
    -0.06
     Mine
    -0.06
    rgb
    -0.06
    _fragment
    -0.06
     安
    -0.06
    POSITIVE LOGITS
    ्दर
    0.07
     narc
    0.06
     (++
    0.06
     oui
    0.06
     především
    0.06
    итом
    0.06
     MMI
    0.06
     español
    0.06
     кер
    0.06
    0.06
    Act Density 0.046%

    No Known Activations