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

    Neuronpedia

    INDEX
    Explanations

    mathematical derivations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     വന്ന
    -0.08
     Chron
    -0.08
    Archives
    -0.08
    urgo
    -0.07
     chron
    -0.07
     satt
    -0.07
    Chron
    -0.07
     ഇയ
    -0.07
     reps
    -0.07
     alph
    -0.07
    POSITIVE LOGITS
     erhöhen
    0.08
    leave
    0.08
     לצ
    0.08
    ાણા
    0.08
    일보
    0.07
    امن
    0.07
    (ix
    0.07
    estre
    0.07
     празд
    0.07
     именно
    0.07
    Act Density 0.160%

    No Known Activations