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

    Neuronpedia

    INDEX
    Explanations

    setting up scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atque
    0.43
     Astron
    0.43
    мено
    0.42
    証
    0.42
     증
    0.41
    Episodes
    0.40
     продов
    0.40
     afterthought
    0.40
    ੀ
    0.39
    áš
    0.38
    POSITIVE LOGITS
     proteins
    0.47
    proteins
    0.44
    ដូច្ន
    0.44
     Proteins
    0.43
    <-
    0.43
     Solubility
    0.42
     noirâtres
    0.41
     stej
    0.41
     carbohydrates
    0.41
     informacija
    0.41
    Act Density 0.004%

    No Known Activations