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

    Neuronpedia

    INDEX
    Explanations

    list items and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     espiritual
    0.74
    ónico
    0.69
     сейчас
    0.68
    ungkinkan
    0.68
     desta
    0.66
     biasa
    0.65
     efeitos
    0.65
     causas
    0.64
    yl
    0.64
     Spiritual
    0.63
    POSITIVE LOGITS
     고객
    0.83
    哿
    0.81
     객
    0.79
    ју
    0.76
     번째
    0.76
    ைட்
    0.76
     최고의
    0.76
    𝐨
    0.76
    公子
    0.75
    ст
    0.75
    Act Density 0.000%

    No Known Activations