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

    Neuronpedia

    INDEX
    Explanations

    lists and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    з
    0.49
    лед
    0.48
    chromiumfx
    0.45
    im
    0.44
    rind
    0.44
    رز
    0.43
     footpath
    0.43
    ен
    0.43
     einf
    0.43
     Voltage
    0.42
    POSITIVE LOGITS
    ता
    0.51
     многи
    0.51
    會
    0.49
    पु
    0.49
     introns
    0.47
     allons
    0.46
    し
    0.45
    setInt
    0.45
    交易所
    0.45
    騇
    0.44
    Act Density 0.000%

    No Known Activations