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

    Neuronpedia

    INDEX
    Explanations

    twitter thread

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ins
    0.43
    ফ
    0.42
     Normalmente
    0.41
     destroyed
    0.40
     horribly
    0.40
    hf
    0.39
    Ip
    0.39
    Large
    0.39
    Um
    0.39
     ክፍ
    0.39
    POSITIVE LOGITS
     पहलू
    0.45
     apology
    0.45
     мав
    0.44
     ओलंपिक
    0.43
     девя
    0.43
    ции
    0.43
     переписи
    0.43
     уйнарга
    0.43
     தங்கள்
    0.42
     спорттук
    0.42
    Act Density 0.001%

    No Known Activations