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

    Neuronpedia

    INDEX
    Explanations

    numbers like 101

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اتي
    0.44
    ид
    0.38
    律
    0.38
    พ์
    0.38
    ാഗ
    0.37
    ואר
    0.37
    ாள
    0.37
    िं
    0.37
    ებთ
    0.37
    })+
    0.36
    POSITIVE LOGITS
    ne
    0.42
    dal
    0.40
     padding
    0.39
     dal
    0.39
    νου
    0.39
     préf
    0.39
    iel
    0.38
     sûr
    0.37
    ctal
    0.37
     Dalmat
    0.37
    Act Density 0.006%

    No Known Activations