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

    Neuronpedia

    INDEX
    Explanations

    stuck on, move to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bah
    0.41
    ologo
    0.41
    decomp
    0.40
     செயற்க
    0.40
    the
    0.40
     Repl
    0.40
    reg
    0.39
    bells
    0.37
    can
    0.37
    रात
    0.37
    POSITIVE LOGITS
     calculators
    0.45
     calculator
    0.43
     yatırım
    0.42
     nyata
    0.42
     ۋ
    0.41
     rookies
    0.41
     aqueles
    0.41
     pály
    0.40
     savings
    0.40
     countrymen
    0.39
    Act Density 0.001%

    No Known Activations