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

    Neuronpedia

    INDEX
    Explanations

    divisible by 3 or prime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fluence
    0.47
     ट्वी
    0.44
     nymphs
    0.44
     ट्वीट
    0.43
    ற்புத
    0.42
     referees
    0.42
     francs
    0.42
     mexico
    0.42
     peces
    0.42
    Missense
    0.42
    POSITIVE LOGITS
    á
    0.49
     größte
    0.45
     найбіль
    0.45
    door
    0.43
    orld
    0.43
    à
    0.43
    ů
    0.43
    rà
    0.42
    rú
    0.41
    设施
    0.41
    Act Density 0.000%

    No Known Activations