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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (var
    -0.07
     bet
    -0.07
     CAL
    -0.07
     loses
    -0.07
     implicitly
    -0.06
    ítulo
    -0.06
     filme
    -0.06
    inct
    -0.06
     insists
    -0.06
    FS
    -0.06
    POSITIVE LOGITS
     κον
    0.07
    regon
    0.07
    ammu
    0.07
     öyle
    0.07
    riteln
    0.07
     }*/↵↵
    0.06
     इतन
    0.06
     tão
    0.06
     QFile
    0.06
     ^↵
    0.06
    Act Density 0.007%

    No Known Activations