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

    Neuronpedia

    INDEX
    Explanations

    forming a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ahuv
    0.54
     watchlist
    0.47
    🚨
    0.47
    ᡵ
    0.47
    𝐇
    0.46
    𝗛
    0.46
     utilisent
    0.46
    রির
    0.46
    ꞎ
    0.46
    meters
    0.46
    POSITIVE LOGITS
     bal
    0.45
     αρχ
    0.45
    信心
    0.43
     والص
    0.42
    Cell
    0.41
     اقبال
    0.41
     Cell
    0.41
     الخلا
    0.41
     कानपुर
    0.40
    BasePath
    0.40
    Act Density 0.003%

    No Known Activations