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

    Neuronpedia

    INDEX
    Explanations

    places and their affiliations

    np_acts-logits-general · gemini-2.5-flash-lite

    geopolitical entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ம்
    0.51
    й
    0.50
    ويه
    0.49
     هڪ
    0.48
    <unused653>
    0.48
    ين
    0.48
     asistencia
    0.47
     bás
    0.46
     as
    0.46
     كه
    0.45
    POSITIVE LOGITS
    ۰
    0.50
    。
    0.48
    >
    0.48
    ار
    0.46
    -
    0.45
     attorney
    0.43
    र्फ
    0.41
    Nel
    0.40
    रम
    0.40
    Q
    0.40
    Act Density 1.593%

    No Known Activations