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

    Neuronpedia

    INDEX
    Explanations

    obligation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    1.10
     be
    1.05
    د
    1.02
    ።
    1.02
     are
    0.98
    ことなく
    0.97
    ला
    0.95
    お金
    0.95
    ى
    0.95
    ት
    0.95
    POSITIVE LOGITS
     to
    1.19
     oblig
    1.13
     obligation
    1.08
    to
    1.06
     obliged
    1.05
    ﺭ
    1.05
    ן
    1.01
    لی
    1.00
     obligated
    0.99
     Obl
    0.98
    Act Density 0.011%

    No Known Activations