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

    Neuronpedia

    INDEX
    Explanations

    possessive of a/the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.52
    да
    0.42
    et
    0.42
    ла
    0.40
    ,
    0.37
    на
    0.36
    il
    0.36
     variations
    0.35
    as
    0.34
    }]
    0.34
    POSITIVE LOGITS
    0.59
    ется
    0.43
    не
    0.41
     của
    0.41
    ４
    0.39
    ные
    0.39
    larını
    0.39
    étais
    0.38
    éducation
    0.38
    räume
    0.38
    Act Density 0.217%

    No Known Activations