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

    Neuronpedia

    INDEX
    Explanations

    acquisitions, medium-sized, questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ={
    0.41
    =%
    0.41
    =[
    0.39
     %
    0.38
    남
    0.37
     fueran
    0.36
    FAIL
    0.35
     Ew
    0.35
    म्मा
    0.34
    Nam
    0.34
    POSITIVE LOGITS
    ชัย
    0.40
    ँच
    0.38
     krä
    0.38
    ayad
    0.38
    бей
    0.37
    LongNumber
    0.37
    EndY
    0.37
     uzun
    0.37
     identifiers
    0.36
    loj
    0.36
    Act Density 0.001%

    No Known Activations