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

    Neuronpedia

    INDEX
    Explanations

    direct integration or specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Toute
    0.55
     geändert
    0.47
     possibilités
    0.47
     boilers
    0.46
     rekonstru
    0.46
     atteindre
    0.46
     числе
    0.45
     alternativas
    0.45
     ře
    0.45
    anh
    0.44
    POSITIVE LOGITS
     errorMessage
    0.57
    ItemStack
    0.50
     напрямую
    0.47
    '
    0.46
    scheduler
    0.45
     subunit
    0.44
    swap
    0.43
    вым
    0.43
    errorMessage
    0.42
    ementara
    0.42
    Act Density 0.007%

    No Known Activations