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

    Neuronpedia

    INDEX
    Explanations

    professional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ps
    -0.08
     ctypes
    -0.07
    秉持
    -0.06
    andalone
    -0.06
    بسي
    -0.06
    党校
    -0.06
    	Created
    -0.06
     acompañ
    -0.06
     Cs
    -0.06
    轩辕
    -0.06
    POSITIVE LOGITS
    им
    0.08
    🎶
    0.07
    ueur
    0.07
    😛
    0.07
    캘
    0.07
    TURN
    0.07
    SCAN
    0.06
    ==========↵
    0.06
    fection
    0.06
    ====↵
    0.06
    Act Density 0.003%

    No Known Activations