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

    Neuronpedia

    INDEX
    Explanations

    recreating or reconstructing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _GP
    -0.07
    PLL
    -0.07
     embar
    -0.07
     OUTPUT
    -0.07
     bystand
    -0.07
     Blackhawks
    -0.06
     AVCapture
    -0.06
     obj
    -0.06
    거나
    -0.06
    )){↵
    -0.06
    POSITIVE LOGITS
     Inf
    0.07
     Saw
    0.06
    Help
    0.06
    expression
    0.06
    braska
    0.06
    \n
    0.06
    	internal
    0.06
     와
    0.06
     атмос
    0.06
    ogene
    0.06
    Act Density 0.157%

    No Known Activations