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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سنة
    -0.08
     tuaj
    -0.08
    ற்று
    -0.08
     리뷰
    -0.07
    ൻ
    -0.07
     seul
    -0.07
     ছব
    -0.07
     паведам
    -0.07
     الدرا
    -0.07
    prt
    -0.07
    POSITIVE LOGITS
     temas
    0.09
     musique
    0.09
     bidang
    0.08
     Hop
    0.08
    Hop
    0.08
     philanth
    0.08
     Sachen
    0.08
     terrorism
    0.08
     sexuality
    0.08
     spirituality
    0.08
    Act Density 0.210%

    No Known Activations