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

    Neuronpedia

    INDEX
    Explanations

    ethical and legal standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.60
    1
    1.56
    g
    1.41
    А
    1.05
    the
    1.02
     चला
    1.01
    １
    0.99
    ט
    0.98
    ta
    0.97
     हरा
    0.97
    POSITIVE LOGITS
    :
    1.30
    н
    1.10
    ن
    1.02
    ERVER
    1.02
    ン
    1.02
    нский
    1.00
    at
    0.98
    are
    0.97
    νει
    0.96
     Hrvatske
    0.95
    Act Density 0.000%

    No Known Activations