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

    Neuronpedia

    INDEX
    Explanations

    digital overload

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     огромное
    0.42
     outdated
    0.38
     ))
    0.37
     নারী
    0.37
     सिव
    0.36
    routerProps
    0.35
    istory
    0.34
     goes
    0.34
     defy
    0.34
    FullPath
    0.33
    POSITIVE LOGITS
    менте
    0.40
     تاز
    0.40
    相対
    0.40
    แต่
    0.39
    addNew
    0.39
    靱
    0.38
    வைத்து
    0.38
     polycrystalline
    0.38
    btnLogout
    0.38
    ziehung
    0.37
    Act Density 0.001%

    No Known Activations