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

    Neuronpedia

    INDEX
    Explanations

    what is X?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RU
    0.47
     Ruto
    0.46
     ALEX
    0.45
     lej
    0.45
     rende
    0.44
     koncent
    0.44
     KI
    0.43
     dve
    0.42
     RI
    0.42
     ri
    0.42
    POSITIVE LOGITS
     آغاز
    0.48
    Entrepreneur
    0.47
    idespread
    0.47
    About
    0.46
    iectasis
    0.46
     பெற்று
    0.45
     અન્ય
    0.45
    ement
    0.45
    ชื่อ
    0.45
     virtually
    0.45
    Act Density 0.001%

    No Known Activations