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

    Neuronpedia

    INDEX
    Explanations

    calculation examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    十三
    0.48
    十一
    0.48
    ⑬
    0.45
     Thirteen
    0.45
     thirteen
    0.44
    Aprend
    0.41
     xiii
    0.40
    ۱۳
    0.40
    යා
    0.40
    tingham
    0.40
    POSITIVE LOGITS
     register
    0.44
    register
    0.42
     достав
    0.42
    UNC
    0.41
     $+
    0.40
     misc
    0.39
     Misc
    0.39
     REGISTER
    0.38
     prosper
    0.37
     witnesses
    0.37
    Act Density 0.011%

    No Known Activations