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

    Neuronpedia

    INDEX
    Explanations

    code keywords and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     escorted
    0.46
    疱
    0.40
     antibiotic
    0.39
     fortress
    0.39
    य्
    0.38
     petrochemical
    0.38
     sweetened
    0.38
     MINISTRY
    0.38
    طع
    0.38
     streamed
    0.38
    POSITIVE LOGITS
    {\
    0.86
    }{\
    0.62
     {\
    0.59
    {
    0.57
     ${\
    0.55
    *{\
    0.54
    {{\
    0.49
    newcommand
    0.47
    {"
    0.46
    {@
    0.46
    Act Density 0.000%

    No Known Activations