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

    Neuronpedia

    INDEX
    Explanations

    currently undergoing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.78
    m
    0.78
    0.72
     damper
    0.68
     L
    0.67
    nT
    0.66
     scaled
    0.66
     Lof
    0.66
     sched
    0.64
     echelon
    0.64
    POSITIVE LOGITS
    恁
    0.83
    اري
    0.82
    Très
    0.82
    കേ
    0.79
    为例
    0.79
     denn
    0.78
     ressemble
    0.78
    XYGEN
    0.78
    امي
    0.78
    ARIO
    0.76
    Act Density 0.001%

    No Known Activations