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

    Neuronpedia

    INDEX
    Explanations

    final declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adrat
    1.94
     empêcher
    1.80
     powod
    1.76
    alysis
    1.76
    ból
    1.69
     rupani
    1.68
    acking
    1.68
    stdout
    1.67
    𝑜
    1.67
     lancé
    1.65
    POSITIVE LOGITS
    اں
    1.78
    een
    1.63
    м
    1.58
    зон
    1.51
    e
    1.42
    го
    1.37
     puluh
    1.35
     dive
    1.34
     wardrobe
    1.31
    সংখ্যক
    1.28
    Act Density 0.001%

    No Known Activations