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

    Neuronpedia

    INDEX
    Explanations

    various language endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    특별시
    2.36
    ד
    2.34
     وعلى
    2.30
    هه
    2.06
    ী
    2.00
    رى
    1.95
    ق
    1.94
    nels
    1.91
    лни
    1.88
    ن
    1.84
    POSITIVE LOGITS
     volna
    2.31
    可以
    1.77
    П
    1.76
    が高
    1.71
    gerald
    1.70
    한
    1.70
    weight
    1.64
    おります
    1.63
    ación
    1.62
    पी
    1.62
    Act Density 0.029%

    No Known Activations