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

    Neuronpedia

    INDEX
    Explanations

    latex equation labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ైనా
    0.39
    вица
    0.36
    determination
    0.36
    держание
    0.36
    тельная
    0.35
    embrie
    0.35
    azoline
    0.35
    󠁥
    0.35
    Trib
    0.34
    ិច
    0.34
    POSITIVE LOGITS
     label
    0.78
    label
    0.77
    Label
    0.64
     Label
    0.63
     labels
    0.62
     LABEL
    0.62
     Labels
    0.57
    标签
    0.55
    LABEL
    0.54
    ラベル
    0.53
    Act Density 0.000%

    No Known Activations