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

    Neuronpedia

    INDEX
    Explanations

    non-english languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Consumer
    0.48
    筮
    0.45
    Decoder
    0.44
     парламент
    0.42
    パス
    0.41
    ரீ
    0.41
    Classpath
    0.41
    Inspection
    0.41
     очи
    0.40
     О
    0.40
    POSITIVE LOGITS
     էին
    0.46
    ალა
    0.46
     avevano
    0.46
     vehement
    0.45
     byly
    0.44
    ellig
    0.44
     भी
    0.43
     były
    0.43
     hadden
    0.43
    τέρα
    0.43
    Act Density 0.003%

    No Known Activations