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

    Neuronpedia

    INDEX
    Explanations

    end of turn

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ያው
    0.78
     Conv
    0.74
     palab
    0.68
     Serv
    0.67
    ባቸው
    0.66
    MenuView
    0.65
     крови
    0.65
    स्ते
    0.64
     Dropout
    0.63
     Principle
    0.63
    POSITIVE LOGITS
    eking
    0.71
    >')
    0.66
    ittu
    0.62
     dating
    0.61
     muk
    0.61
    rera
    0.60
     কবর
    0.59
     mutual
    0.59
     hok
    0.58
    曹
    0.57
    Act Density 0.007%

    No Known Activations