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

    Neuronpedia

    INDEX
    Explanations

    license and version headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    APPE
    0.41
    ალაქ
    0.38
    Traversal
    0.37
    იან
    0.36
    ሽታ
    0.36
    "+"|".
    0.36
    proficiency
    0.36
    walkers
    0.36
    പക്ഷ
    0.35
     millón
    0.35
    POSITIVE LOGITS
     file
    0.65
     File
    0.63
     файл
    0.63
     파일
    0.61
     文件
    0.59
     Copyright
    0.58
     Datei
    0.55
     copyright
    0.53
     파일을
    0.53
    file
    0.50
    Act Density 0.006%

    No Known Activations