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

    Neuronpedia

    INDEX
    Explanations

    regex flags like g or gi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cpuCycle
    0.80
    ccncc
    0.76
    eksi
    0.73
    스는
    0.72
    0.71
    DanhMucSP
    0.71
    featuresMatrix
    0.70
    events
    0.70
    ensión
    0.69
    gdock
    0.69
    POSITIVE LOGITS
     l
    0.67
     I
    0.64
    。
    0.58
    在
    0.57
     。
    0.56
    .
    0.56
     la
    0.55
    ۔
    0.55
    <0xE3>
    0.53
     magazine
    0.52
    Act Density 0.006%

    No Known Activations