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

    Neuronpedia

    INDEX
    Explanations

    wen / wend / Wendy / Wentworth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thin
    0.41
    supp
    0.39
    กัน
    0.38
    Supp
    0.37
    racial
    0.36
     মির
    0.36
    cnico
    0.36
    咉
    0.35
    ral
    0.35
     Please
    0.35
    POSITIVE LOGITS
     ставкалары
    0.38
     Matrices
    0.38
    Ŷ
    0.37
     phospho
    0.37
     машиналарын
    0.37
    +"|
    0.36
     করলেন
    0.35
     μορ
    0.35
    Matrices
    0.35
    礡
    0.35
    Act Density 0.003%

    No Known Activations