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

    Neuronpedia

    INDEX
    Explanations

    i in range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kurt
    0.60
    ેલ
    0.59
    cribes
    0.58
    ({})
    0.58
     pure
    0.58
     olt
    0.58
     lối
    0.57
    aminated
    0.57
    pure
    0.56
     Selective
    0.56
    POSITIVE LOGITS
     range
    2.54
    range
    2.18
     Range
    2.08
    Range
    2.03
     ranges
    1.94
     ranging
    1.94
     RANGE
    1.76
     Ranges
    1.64
    ranging
    1.63
    RANGE
    1.56
    Act Density 0.209%

    No Known Activations