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

    Neuronpedia

    INDEX
    Explanations

    data loss prevention and documentatio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ިން
    0.71
    ylmethyl
    0.63
    perme
    0.63
    тся
    0.62
    وری
    0.62
    មើ
    0.60
    ্লে
    0.59
    цию
    0.58
    osphere
    0.58
    >\<^
    0.58
    POSITIVE LOGITS
     sebuah
    0.81
     Alguns
    0.77
     deze
    0.77
    こんな
    0.76
    l
    0.76
     dulu
    0.75
     relatório
    0.74
     også
    0.74
     queste
    0.74
     também
    0.73
    Act Density 0.994%

    No Known Activations