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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbol packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дук
    0.40
    ットン
    0.38
    كمة
    0.38
     imaginations
    0.38
     Oggi
    0.37
     हॉस्पिटल
    0.36
     Гуляць
    0.36
    ্টো
    0.36
    লির
    0.36
     Баскетбол
    0.36
    POSITIVE LOGITS
     c
    0.36
     host
    0.36
     wú
    0.35
    $
    0.35
     $
    0.35
    0.34
    est
    0.33
     res
    0.33
    }$
    0.33
     CE
    0.33
    Act Density 0.000%

    No Known Activations