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

    Neuronpedia

    INDEX
    Explanations

    magically

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hallmark
    -0.06
     Courtesy
    -0.06
    Som
    -0.06
    peon
    -0.06
     gio
    -0.06
    farm
    -0.06
    _timeline
    -0.06
    Substring
    -0.06
    Layer
    -0.06
     disdain
    -0.06
    POSITIVE LOGITS
    arDown
    0.06
     만족
    0.06
     praying
    0.06
     kil
    0.06
    τοι
    0.06
     ############
    0.06
    ored
    0.06
     řád
    0.06
    �
    0.06
    概
    0.06
    Act Density 0.000%

    No Known Activations