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

    Neuronpedia

    INDEX
    Explanations

    Legal terms and definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     psychos
    -0.09
     whichever
    -0.09
    asters
    -0.08
     whatever
    -0.08
     behavioral
    -0.08
     Ru
    -0.08
    ISTS
    -0.08
    ÉS
    -0.07
     actuales
    -0.07
     Posters
    -0.07
    POSITIVE LOGITS
     necessita
    0.08
    نسية
    0.08
     NATIONAL
    0.08
     (‘
    0.08
    તમાં
    0.07
    ناف
    0.07
     massif
    0.07
     appell
    0.07
    未经
    0.07
    θυν
    0.07
    Act Density 0.007%

    No Known Activations