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

    Neuronpedia

    INDEX
    Explanations

    empty list representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    1.64
    for
    1.57
    E
    1.56
    O
    1.52
    В
    1.49
    S
    1.48
    à
    1.48
    In
    1.47
    line
    1.47
    У
    1.46
    POSITIVE LOGITS
     [];
    2.03
     "";
    1.80
     获取
    1.75
     []
    1.74
     obter
    1.73
     '';
    1.72
     None
    1.67
     txtbtn
    1.64
     getColor
    1.63
     findViewById
    1.61
    Act Density 1.452%

    No Known Activations