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

    Neuronpedia

    INDEX
    Explanations

    sentiment expression I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.27
    ν
    0.27
    တ်
    0.27
    ници
    0.27
    рому
    0.26
    তেন
    0.26
    стру
    0.25
    ር
    0.25
    نون
    0.25
     hautes
    0.25
    POSITIVE LOGITS
    İ
    0.35
    lt
    0.33
    ls
    0.33
     İ
    0.31
    ly
    0.31
    lk
    0.30
    ic
    0.30
    lą
    0.30
     incroyable
    0.30
    kh
    0.30
    Act Density 0.000%

    No Known Activations