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

    Neuronpedia

    INDEX
    Explanations

    mild symptoms or pain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    covering
    0.50
    irce
    0.48
    oinette
    0.44
    nat
    0.42
    bestos
    0.42
    inert
    0.41
     ખાસ
    0.41
    Hitting
    0.40
     الحكوم
    0.40
    rene
    0.40
    POSITIVE LOGITS
     prairies
    0.40
     필
    0.40
    VerFile
    0.39
     comps
    0.39
     ziua
    0.39
    分隔
    0.38
    Ai
    0.38
     Má
    0.38
     отста
    0.38
     Edg
    0.38
    Act Density 0.001%

    No Known Activations