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

    Neuronpedia

    INDEX
    Explanations

    Clinical Support Worker / Healthcare Assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     R
    1.31
     l
    1.23
     r
    1.21
     F
    1.20
    שת
    1.20
    ue
    1.20
     seemingly
    1.20
     S
    1.19
    ug
    1.18
     N
    1.14
    POSITIVE LOGITS
    ский
    1.55
     américain
    1.52
     lainnya
    1.45
     vitesses
    1.41
    لم
    1.41
    те
    1.40
     Amérique
    1.40
     huile
    1.38
     extérieure
    1.37
    ляется
    1.33
    Act Density 0.000%

    No Known Activations