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

    Neuronpedia

    INDEX
    Explanations

    neutrons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ur
    1.16
    zei
    0.94
    ga
    0.93
    er
    0.91
    f
    0.91
    ﻞ
    0.90
    č
    0.88
    ir
    0.87
    d
    0.86
    çamento
    0.85
    POSITIVE LOGITS
     pouces
    0.80
    ែម
    0.80
    0.79
    ぞれ
    0.78
    на
    0.78
     toutefois
    0.77
     তবে
    0.77
    ков
    0.77
     finestra
    0.77
    敀
    0.77
    Act Density 0.001%

    No Known Activations