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

    Neuronpedia

    INDEX
    Explanations

    convert fraction, baby tees, list[ ]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -">
    0.83
    –
    0.73
    脑袋
    0.70
    asible
    0.68
    FixedWidth
    0.67
    −</
    0.67
    0.66
     trafi
    0.66
    τερ
    0.65
     leap
    0.64
    POSITIVE LOGITS
     पारा
    0.64
     Str
    0.64
    বত
    0.63
    AMINATION
    0.62
    の頃
    0.62
    cretsiz
    0.61
    beck
    0.61
     Стра
    0.59
    С
    0.59
     sezon
    0.59
    Act Density 0.000%

    No Known Activations