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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or initialisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    跇
    0.47
     недвижи
    0.46
    㳒
    0.46
    🕕
    0.45
    ementerian
    0.45
    ObjectMapper
    0.45
     Ethereum
    0.44
    喍
    0.44
    🔳
    0.44
    дон
    0.43
    POSITIVE LOGITS
     C
    0.86
     B
    0.84
     S
    0.84
     T
    0.82
     P
    0.82
     N
    0.76
     R
    0.75
     D
    0.73
     M
    0.72
     H
    0.71
    Act Density 0.106%

    No Known Activations