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

    Neuronpedia

    INDEX
    Explanations

    personal narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arges
    -0.07
     빨
    -0.06
    _ctrl
    -0.06
    ViewModel
    -0.06
    _pitch
    -0.06
     UTF
    -0.06
    	
↵	
↵
    -0.06
    	controller
    -0.06
     creatively
    -0.06
     autobiography
    -0.06
    POSITIVE LOGITS
     Tottenham
    0.07
     iler
    0.06
     thick
    0.06
     interfering
    0.06
    (size
    0.06
     أث
    0.06
    LOT
    0.06
    alsex
    0.06
     Централь
    0.06
    ordes
    0.06
    Act Density 0.029%

    No Known Activations