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

    Neuronpedia

    INDEX
    Explanations

    programming data types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     går
    -0.09
     LIABLE
    -0.08
     diferents
    -0.07
     saham
    -0.07
     abit
    -0.07
    �
    -0.07
     cramped
    -0.07
     istor
    -0.07
    cheme
    -0.07
     další
    -0.07
    POSITIVE LOGITS
    /non
    0.09
     válido
    0.09
     بودن
    0.09
    且
    0.08
     nominees
    0.08
     Everywhere
    0.08
     בלבד
    0.08
    -containing
    0.07
     ಪರ
    0.07
     সংখ্যা
    0.07
    Act Density 0.026%

    No Known Activations