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

    Neuronpedia

    INDEX
    Explanations

    define or explain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وارد
    0.26
    ټر
    0.25
     König
    0.24
     Eing
    0.24
    ගෙන
    0.23
     Taw
    0.23
     Liebe
    0.23
     Hubert
    0.23
     récentes
    0.23
     bereits
    0.23
    POSITIVE LOGITS
     soldering
    0.28
     skyrock
    0.27
     certainly
    0.26
     是
    0.26
     means
    0.26
     MEANS
    0.26
     differs
    0.25
    是非常
    0.25
    是最
    0.25
     involves
    0.25
    Act Density 0.079%

    No Known Activations