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

    Neuronpedia

    INDEX
    Explanations

    from followed by space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বাঁধ
    0.44
    爯
    0.43
    '_{\
    0.41
    ্বিক
    0.40
    )^\
    0.40
     حسين
    0.40
     минима
    0.39
     മുഖ്യമ
    0.39
     बनाना
    0.39
     asociada
    0.38
    POSITIVE LOGITS
     Novel
    0.40
    ANO
    0.39
     groom
    0.38
     Eli
    0.38
    ļ
    0.38
    ano
    0.37
    Ut
    0.37
     preprint
    0.37
     Sect
    0.37
    unce
    0.37
    Act Density 0.000%

    No Known Activations