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

    Neuronpedia

    INDEX
    Explanations

    default system settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lahir
    0.51
     гимна
    0.42
    讓他
    0.42
     写真
    0.42
     magari
    0.42
    ക്കണം
    0.42
     Englishmen
    0.42
     biar
    0.42
     aspirations
    0.41
     言っ
    0.41
    POSITIVE LOGITS
     system
    0.71
    系统
    0.67
    默认
    0.67
     default
    0.66
     시스템
    0.63
     automatically
    0.60
    官方
    0.59
    default
    0.58
     ODBC
    0.58
    Default
    0.57
    Act Density 0.516%

    No Known Activations