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

    Neuronpedia

    INDEX
    Explanations

    problems, consequences, solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    niers
    0.43
     വിഷയ
    0.40
    ieres
    0.40
    edent
    0.39
    प्ताह
    0.38
    तेल
    0.38
    瀉
    0.38
     aulas
    0.37
    Компания
    0.37
    狨
    0.37
    POSITIVE LOGITS
     powerfully
    0.41
     Ow
    0.41
     bounded
    0.37
     square
    0.37
     casc
    0.37
     PWR
    0.36
    Rr
    0.36
     PP
    0.36
     PPI
    0.36
     uğ
    0.36
    Act Density 0.000%

    No Known Activations