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

    Neuronpedia

    INDEX
    Explanations

    citation numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ada
    0.42
     Accord
    0.39
    残念
    0.38
     Av
    0.37
    Tre
    0.37
    绦
    0.37
     Ag
    0.37
     Mol
    0.37
    Sol
    0.37
     AsRef
    0.36
    POSITIVE LOGITS
     vatth
    0.41
    bukkit
    0.39
     вулка
    0.37
     यूरो
    0.37
    attuale
    0.37
    kiye
    0.36
    的情况下
    0.36
    ಿತಿ
    0.36
     セット
    0.35
    普通の
    0.35
    Act Density 0.000%

    No Known Activations