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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    数为
    0.48
     لوبو
    0.44
    aphore
    0.43
    交换
    0.43
     ખો
    0.42
     recalculated
    0.41
     ஆக
    0.41
     REFERENCE
    0.40
    ULO
    0.40
     substituted
    0.40
    POSITIVE LOGITS
    Emer
    0.53
    ह
    0.47
     निघ
    0.44
    álních
    0.44
    สำ
    0.44
    לע
    0.44
    elige
    0.43
     accidens
    0.43
     sorties
    0.43
     déjà
    0.43
    Act Density 0.005%

    No Known Activations