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

    Neuronpedia

    INDEX
    Explanations

    programming language types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝓽
    1.84
    𝓶
    1.76
    \%.
    1.71
    ை
    1.68
    вање
    1.67
    І
    1.65
     denn
    1.64
    یه
    1.64
    𝓪
    1.63
    Р
    1.62
    POSITIVE LOGITS
     glad
    2.21
     coinc
    2.09
     shout
    1.95
     गौरतलब
    1.92
    屽
    1.90
     congru
    1.89
     endian
    1.79
     HAZ
    1.79
     glimpse
    1.77
     eras
    1.77
    Act Density 0.054%

    No Known Activations