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

    Neuronpedia

    INDEX
    Explanations

    around certain units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    رځ
    0.48
    0.47
    ʀ
    0.46
    segaretro
    0.44
    壹章
    0.44
    褛
    0.44
     urbano
    0.43
    unità
    0.43
    anning
    0.42
    getattr
    0.42
    POSITIVE LOGITS
    SP
    0.44
    ASI
    0.42
     HB
    0.42
    Hb
    0.41
     пр
    0.40
    STEN
    0.40
     AND
    0.39
     sprint
    0.38
    Ether
    0.38
     wad
    0.37
    Act Density 0.004%

    No Known Activations