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

    Neuronpedia

    INDEX
    Explanations

    scroll down to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     swinging
    0.75
     straightened
    0.68
     simplex
    0.66
     simultaneously
    0.66
    dorf
    0.66
     overt
    0.66
     dock
    0.64
     зали
    0.64
    s
    0.64
    producing
    0.63
    POSITIVE LOGITS
     até
    0.94
     till
    0.94
    ScrollView
    0.93
     ಮತ್ತು
    0.93
    RecyclerView
    0.92
    scrollView
    0.92
    াক্ত
    0.92
    )%>%
    0.91
    Playlist
    0.90
     עד
    0.89
    Act Density 0.004%

    No Known Activations