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

    Neuronpedia

    INDEX
    Explanations

    initials before names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ාව
    0.49
     بمعنى
    0.48
    ഥി
    0.48
     impon
    0.46
    setwd
    0.44
    fcast
    0.43
    コンセプト
    0.43
     fokus
    0.43
    queryset
    0.42
    គ្ន
    0.42
    POSITIVE LOGITS
     C
    0.60
     J
    0.58
     T
    0.56
     L
    0.56
     Л
    0.56
     R
    0.55
     D
    0.55
     A
    0.54
     M
    0.54
     Р
    0.54
    Act Density 0.063%

    No Known Activations