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

    Neuronpedia

    INDEX
    Explanations

    word families

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    1.82
    ת
    1.69
    ی
    1.67
    ംഗ്
    1.63
    nin
    1.48
    ك
    1.48
    ﺎ
    1.41
    не
    1.38
    ться
    1.38
    Jährige
    1.37
    POSITIVE LOGITS
    ட
    1.59
     rechaz
    1.56
    ad
    1.53
     determinado
    1.48
    ER
    1.45
     termasuk
    1.45
    が無い
    1.44
     certos
    1.44
    az
    1.43
     palabras
    1.43
    Act Density 0.001%

    No Known Activations