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

    Neuronpedia

    INDEX
    Explanations

    fur, fursona, furries, fur babies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    লে
    1.25
    ↵↵
    1.21
    ד
    1.13
    ע
    1.11
    IM
    1.09
    ために
    1.07
    𝙡
    1.05
    大
    1.04
    我对
    1.03
    ح
    1.00
    POSITIVE LOGITS
    z
    1.54
    n
    1.26
     by
    1.09
    اری
    1.08
    k
    1.08
     There
    1.03
     The
    1.02
    cerr
    1.01
    ем
    0.98
    ко
    0.98
    Act Density 0.001%

    No Known Activations