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

    Neuronpedia

    INDEX
    Explanations

    initiate action or proposal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.52
    ون
    0.52
     pendapat
    0.49
    ८
    0.48
    امر
    0.47
    :'.
    0.47
    ﺍ
    0.47
     जानना
    0.46
    plantation
    0.46
    ۴
    0.46
    POSITIVE LOGITS
     illuminate
    0.53
    rodite
    0.52
    enza
    0.49
    nea
    0.49
    dor
    0.48
    ting
    0.47
     herv
    0.47
     creat
    0.46
     fulfill
    0.45
     a
    0.44
    Act Density 0.135%

    No Known Activations