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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }$).
    0.55
    to
    0.52
    the
    0.52
    Integrante
    0.50
    such
    0.50
    ﺎ
    0.48
    })}
    0.48
    ﺰ
    0.47
    Advisor
    0.47
     Ahí
    0.46
    POSITIVE LOGITS
    ❤️❤️
    0.65
    ل
    0.62
    िक
    0.59
    υ
    0.55
    ে
    0.52
    oq
    0.52
    但这
    0.48
    ه
    0.48
    लिंग
    0.48
    分之一
    0.48
    Act Density 0.258%

    No Known Activations