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

    Neuronpedia

    INDEX
    Explanations

    adjust quantities and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.60
    [
    0.52
     Radio
    0.51
    -
    0.50
     Regional
    0.48
    /
    0.48
     will
    0.47
    Radio
    0.47
     Col
    0.47
     reaction
    0.46
    POSITIVE LOGITS
     artères
    0.57
     postérieures
    0.53
    迪士
    0.52
    ﷼
    0.50
    ㄼ
    0.50
    ienze
    0.50
     intérêts
    0.49
    ÕES
    0.49
    圴
    0.49
     lézard
    0.49
    Act Density 0.006%

    No Known Activations