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

    Neuronpedia

    INDEX
    Explanations

    Route

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ꒦
    -0.07
    苌
    -0.06
     altitude
    -0.06
     adipiscing
    -0.06
    ideo
    -0.06
    (ChatColor
    -0.06
     :+:
    -0.06
    ым
    -0.06
    withErrors
    -0.06
    处分
    -0.06
    POSITIVE LOGITS
     대부분
    0.08
     Rule
    0.07
    כלכלה
    0.07
     --}}↵
    0.07
     отправ
    0.07
    _terminal
    0.07
    _increase
    0.06
    其中
    0.06
    /B
    0.06
     gist
    0.06
    Act Density 0.001%

    No Known Activations