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

    Neuronpedia

    INDEX
    Explanations

    not strictly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不允许
    0.62
     asla
    0.59
    nicht
    0.58
     nejen
    0.57
     unnecessary
    0.57
     прекрасно
    0.57
    ine
    0.57
     unnecessarily
    0.55
    Gew
    0.55
    Waar
    0.55
    POSITIVE LOGITS
    正式
    0.86
     основных
    0.84
     formal
    0.75
     основные
    0.75
     formalized
    0.75
     formally
    0.72
    主要的
    0.71
    vinced
    0.70
     주요
    0.69
     основным
    0.68
    Act Density 0.424%

    No Known Activations