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

    Neuronpedia

    INDEX
    Explanations

    text before options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Semiconductor
    0.39
     घरात
    0.38
     They
    0.37
    otras
    0.35
     Maschine
    0.35
     Astronom
    0.34
     மேற்க
    0.34
     Overland
    0.34
     semiconductors
    0.33
     шли
    0.33
    POSITIVE LOGITS
    َل
    0.37
    ąd
    0.36
    اطع
    0.36
    ぢ
    0.36
    reviews
    0.36
    prd
    0.36
    help
    0.35
    ف
    0.35
    ądź
    0.34
    sites
    0.34
    Act Density 0.002%

    No Known Activations