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

    Neuronpedia

    INDEX
    Explanations

    https:// or /

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tourne
    0.76
     recherches
    0.74
     ड्र
    0.72
    jande
    0.72
    البه
    0.71
     छठ
    0.71
     Kraj
    0.71
     жо
    0.70
    дни
    0.70
    닝
    0.70
    POSITIVE LOGITS
    liner
    0.84
     }^{-
    0.72
    ='',
    0.71
     باسم
    0.64
    返す
    0.63
    CHEM
    0.63
     아니라
    0.63
    㸽
    0.63
    nam
    0.62
     আলো
    0.61
    Act Density 0.003%

    No Known Activations