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

    Neuronpedia

    INDEX
    Explanations

    process after Ciudad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #{
    0.48
    (#
    0.47
    นอก
    0.46
    javax
    0.44
    destroy
    0.43
    ة
    0.42
    out
    0.42
    #.
    0.41
    $
    0.41
    اسم
    0.41
    POSITIVE LOGITS
     দেবতাদের
    0.57
     woodwork
    0.53
     🌱
    0.52
     cadres
    0.52
     taille
    0.52
     jueces
    0.52
     icono
    0.51
     እነዚህ
    0.51
     hierro
    0.51
     víctimas
    0.50
    Act Density 0.001%

    No Known Activations