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

    Neuronpedia

    INDEX
    Explanations

    measurable metrics KPIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vice
    0.46
    árl
    0.46
     vice
    0.42
    Introducing
    0.39
     conceived
    0.39
    උ
    0.39
     프리
    0.38
     본
    0.38
    emailer
    0.38
    arı
    0.37
    POSITIVE LOGITS
     vuos
    0.44
     movimento
    0.44
     movimentos
    0.42
     Bg
    0.42
     movimenti
    0.41
     menopause
    0.41
    walten
    0.41
     pomo
    0.40
    elift
    0.40
     movement
    0.39
    Act Density 0.000%

    No Known Activations