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

    Neuronpedia

    INDEX
    Explanations

    `\today` marker in LaTeX documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jenigen
    1.05
    ない
    0.98
    ことができる
    0.79
    ലിം
    0.75
    h
    0.71
    lub
    0.71
    นอน
    0.71
    an
    0.70
    әне
    0.70
    น้อง
    0.70
    POSITIVE LOGITS
    ⅼ
    0.80
     rbuf
    0.77
    și
    0.72
    }`
    0.71
    šan
    0.71
    শে
    0.70
    }(
    0.69
    ѕ
    0.69
    ́t
    0.68
    "",
    0.67
    Act Density 0.001%

    No Known Activations