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

    Neuronpedia

    INDEX
    Explanations

    code context or statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.65
    ,
    0.63
    :
    0.60
    ve
    0.55
     S
    0.55
    th
    0.54
    g
    0.52
    ]]
    0.51
    ing
    0.51
    sc
    0.50
    POSITIVE LOGITS
     TouchUtils
    0.51
    िसिटी
    0.50
     திருவ
    0.49
    asiti
    0.49
    OutSize
    0.48
    vykor
    0.48
    ляют
    0.48
    恴
    0.48
     Técnica
    0.48
     могут
    0.48
    Act Density 0.000%

    No Known Activations