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

    Neuronpedia

    INDEX
    Explanations

    on and, Another World, whisky

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :&
    0.52
    im
    0.51
    :(
    0.50
    Ğ
    0.49
    fresh
    0.48
    𝗺
    0.48
    Ĝ
    0.47
    :*
    0.47
    cı
    0.47
    ﻁ
    0.46
    POSITIVE LOGITS
    ным
    0.52
    的中
    0.52
    ных
    0.49
     nhất
    0.48
    ный
    0.48
    ossians
    0.47
     Americana
    0.47
    وها
    0.46
    漬
    0.46
     Sesame
    0.46
    Act Density 0.000%

    No Known Activations