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

    Neuronpedia

    INDEX
    Explanations

    temporary variables in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    方は
    0.44
    宗旨
    0.40
    ᒃ
    0.40
    ជាមួយនឹង
    0.39
    𒆕
    0.38
    চনার
    0.38
    歙
    0.38
    恫
    0.38
    場合は
    0.37
    時は
    0.37
    POSITIVE LOGITS
    tmp
    0.80
     tmp
    0.79
     temp
    0.77
    temp
    0.76
    ;
    0.76
    Tmp
    0.67
     temporary
    0.60
    $;
    0.60
     Temp
    0.60
    dummy
    0.60
    Act Density 0.013%

    No Known Activations