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

    Neuronpedia

    INDEX
    Explanations

    addressing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न
    1.78
    janje
    1.70
    ं
    1.70
     Kirche
    1.63
     sawing
    1.55
    트
    1.55
    т
    1.53
    また
    1.52
    ج
    1.52
    چ
    1.48
    POSITIVE LOGITS
    $('#
    2.16
    𝐞
    2.03
    𝐬
    1.93
    𝐨
    1.92
    사항
    1.90
    𝐥
    1.81
    $('
    1.79
    $(".
    1.76
    ⺆
    1.75
    $("#
    1.71
    Act Density 0.157%

    No Known Activations