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

    Neuronpedia

    INDEX
    Explanations

    arc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gov
    -0.07
    Woman
    -0.07
    IALIZED
    -0.07
     Mater
    -0.07
    reature
    -0.07
    LastName
    -0.07
    FileSystem
    -0.06
     Fellow
    -0.06
    	buff
    -0.06
     females
    -0.06
    POSITIVE LOGITS
     arc
    0.12
    Arc
    0.11
     Arc
    0.11
     arcs
    0.10
     ARC
    0.10
    arc
    0.08
     arcane
    0.08
     Marc
    0.08
    ourg
    0.07
    (arc
    0.07
    Act Density 0.005%

    No Known Activations