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

    Neuronpedia

    INDEX
    Explanations

    AI, PDF, Airplane, Tax, seismic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTS
    0.34
    綀
    0.33
    注重
    0.32
    തില്‍
    0.31
    ೆಗೆ
    0.31
     sano
    0.31
     стрем
    0.31
    何を
    0.31
     เศษ
    0.30
     portanto
    0.30
    POSITIVE LOGITS
    _
    0.65
    2
    0.59
    -
    0.53
    :
    0.46
    .
    0.46
    6
    0.45
    x
    0.44
    4
    0.44
    3
    0.44
    9
    0.43
    Act Density 0.173%

    No Known Activations