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

    Neuronpedia

    INDEX
    Explanations

    counting numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    锞
    0.40
     overheating
    0.39
    (({
    0.38
     프로세
    0.37
     Hast
    0.37
     auditions
    0.37
     unheard
    0.36
     aguj
    0.36
     booting
    0.36
     injections
    0.36
    POSITIVE LOGITS
    olines
    0.43
    tiempo
    0.42
    Find
    0.41
    TypeOf
    0.40
    mines
    0.40
    MINE
    0.40
     Tìm
    0.40
    Wine
    0.40
    scope
    0.40
    abis
    0.40
    Act Density 0.054%

    No Known Activations