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

    Neuronpedia

    INDEX
    Explanations

    August dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     June
    -1.56
    June
    -1.36
     May
    -1.11
     April
    -1.10
     JUNE
    -1.08
    April
    -1.06
    june
    -1.05
     june
    -1.00
     abril
    -0.99
     juin
    -0.98
    POSITIVE LOGITS
     August
    3.06
    August
    2.84
     Aug
    2.33
     авгу
    2.27
     agosto
    2.22
     AUGUST
    2.19
    AUGUST
    2.13
    Aug
    2.08
     august
    2.06
     September
    1.98
    Act Density 0.091%

    No Known Activations