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

    Neuronpedia

    INDEX
    Explanations

    quantity, tracking, triggering, calculating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AGRIC
    0.50
    IAL
    0.48
    льник
    0.46
    lf
    0.45
    lc
    0.44
    FFIC
    0.44
    BO
    0.44
    TA
    0.43
    Burst
    0.42
    ził
    0.42
    POSITIVE LOGITS
    ఖ్య
    0.48
     പ്രച
    0.48
     Udemy
    0.47
     Malware
    0.47
     comics
    0.46
     Vineyard
    0.46
     Discord
    0.45
     ገን
    0.45
     Botox
    0.45
     रेफर
    0.45
    Act Density 0.002%

    No Known Activations