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

    Neuronpedia

    INDEX
    Explanations

    the letter Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Structuring
    0.88
     सपने
    0.85
     التمث
    0.84
     career
    0.83
    iones
    0.81
    coes
    0.80
     desem
    0.80
    জির
    0.80
    Equal
    0.80
    iber
    0.80
    POSITIVE LOGITS
    〢
    1.01
    ဉ်
    0.84
    损失
    0.82
     আহম
    0.81
     আরা
    0.78
    葱
    0.78
    Архівовано
    0.78
    uating
    0.76
     イエロー
    0.76
     smudge
    0.76
    Act Density 0.252%

    No Known Activations