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

    Neuronpedia

    INDEX
    Explanations

    code comments and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ggak
    0.38
    শিকান্ত
    0.37
    ಮುಖ
    0.34
    klärung
    0.34
    เก
    0.33
     الناس
    0.32
    耶稣
    0.32
     옷
    0.32
     thấm
    0.32
    निंग
    0.32
    POSITIVE LOGITS
     /*
    0.49
     //
    0.48
    0
    0.44
    .
    0.43
    ;
    0.42
    x
    0.38
    //
    0.37
     *(
    0.36
     *
    0.35
     Int
    0.35
    Act Density 0.113%

    No Known Activations