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

    Neuronpedia

    INDEX
    Explanations

    hitherto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.29
    ations
    0.28
    r
    0.26
    ing
    0.26
    umu
    0.26
    ATIONS
    0.25
     Naturally
    0.25
     maximized
    0.25
     बदली
    0.25
    িকর
    0.25
    POSITIVE LOGITS
    岛
    0.29
    خيص
    0.28
     ésta
    0.28
    腺
    0.28
    ؎
    0.28
     hitherto
    0.27
    حية
    0.27
     കു
    0.27
    itherto
    0.27
     فلسط
    0.27
    Act Density 0.000%

    No Known Activations