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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     south
    -0.08
    ⌵
    -0.07
        	↵
    -0.07
    停
    -0.07
    inue
    -0.07
    -0.07
     Blue
    -0.07
     cận
    -0.07
    TAIL
    -0.06
    isations
    -0.06
    POSITIVE LOGITS
    ').'
    0.08
     Watching
    0.07
     reacting
    0.07
     Barg
    0.07
    为
    0.07
     kinetics
    0.07
    .EventHandler
    0.07
     Workplace
    0.07
    .Marker
    0.07
     реак
    0.07
    Act Density 0.005%

    No Known Activations