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

    Neuronpedia

    INDEX
    Explanations

    char ** program molecule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Urea
    0.30
    畯
    0.30
    旮
    0.29
    峒
    0.29
     McCormick
    0.28
    古い
    0.28
     पॉलिटी
    0.28
    乱流
    0.27
     Middleware
    0.27
    🗺
    0.27
    POSITIVE LOGITS
    že
    0.30
    ob
    0.27
    }}}}$
    0.27
    Š
    0.26
    }-
    0.26
    apa
    0.26
    $\
    0.25
    altung
    0.25
    áciu
    0.25
     참
    0.25
    Act Density 0.000%

    No Known Activations