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

    Neuronpedia

    INDEX
    Explanations

    clusters of sores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ität
    0.49
     जताई
    0.49
    تباين
    0.48
     单
    0.46
     LDA
    0.44
    ্ন
    0.43
    လှ
    0.42
    üğ
    0.42
    诖
    0.42
    öt
    0.42
    POSITIVE LOGITS
    Cuando
    0.49
    Зак
    0.48
    Gin
    0.47
    ῇ
    0.46
    Somos
    0.45
    aband
    0.44
     وہاں
    0.43
    bagian
    0.43
    Enh
    0.43
    Desc
    0.42
    Act Density 0.001%

    No Known Activations