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

    Neuronpedia

    INDEX
    Explanations

    words starting with ar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.86
    ぞ
    0.86
     آخر
    0.81
    اتھن
    0.80
     Auff
    0.79
    endum
    0.76
    atif
    0.76
    lad
    0.76
    Le
    0.75
     Noch
    0.75
    POSITIVE LOGITS
    ANSAS
    1.39
    idopsis
    1.17
     thaliana
    1.09
     manis
    1.09
    adaşlar
    1.07
    ITECT
    1.07
    ansas
    1.03
     trebui
    1.03
    헹
    1.03
     hsl
    1.03
    Act Density 0.337%

    No Known Activations