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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ge
    0.44
    ge
    0.43
    เก
    0.43
    init
    0.42
     ге
    0.41
    play
    0.40
    .-\
    0.40
    тельстве
    0.40
    lin
    0.39
    ologic
    0.39
    POSITIVE LOGITS
    יש
    0.38
    Jan
    0.37
    Jul
    0.34
     সম্পর্কে
    0.33
    ಿ
    0.33
    ㅑ
    0.33
     PSL
    0.31
     راس
    0.31
     TOL
    0.31
     मंडी
    0.31
    Act Density 0.001%

    No Known Activations