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

    Neuronpedia

    INDEX
    Explanations

    specific definitions and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xmlns
    0.48
    other
    0.47
    relation
    0.45
    অন্য
    0.45
    Import
    0.44
    ost
    0.44
    orgung
    0.44
    orld
    0.43
    quement
    0.43
    ofile
    0.42
    POSITIVE LOGITS
     upregulation
    0.54
     protagon
    0.50
     hedon
    0.47
     acteurs
    0.45
     intermittent
    0.44
     exorc
    0.44
     dystopian
    0.44
     énergie
    0.44
     ár
    0.43
    َا
    0.43
    Act Density 0.017%

    No Known Activations