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

    Neuronpedia

    INDEX
    Explanations

    web3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.63
    ة
    0.62
    ע
    0.53
    infect
    0.52
    east
    0.52
    ;"+
    0.51
    ும்
    0.50
    ுடன்
    0.50
     ouvertes
    0.50
    trem
    0.49
    POSITIVE LOGITS
     Workbook
    0.51
     Các
    0.50
     Heating
    0.48
     Alk
    0.48
     Hvis
    0.48
    ush
    0.47
    鎏
    0.47
     Dans
    0.47
     Herzog
    0.46
     Plac
    0.46
    Act Density 0.000%

    No Known Activations