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

    Neuronpedia

    INDEX
    Explanations

    newlines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ili
    -0.06
     pus
    -0.06
    趣
    -0.06
     ис
    -0.06
    883
    -0.06
     Lil
    -0.06
     silica
    -0.06
     Atlas
    -0.06
     titan
    -0.06
    item
    -0.06
    POSITIVE LOGITS
    	create
    0.07
     UIAlertView
    0.07
     wilderness
    0.06
     CR
    0.06
     Veterans
    0.06
    	Logger
    0.06
     Barrett
    0.06
    	server
    0.06
     create
    0.06
     хими
    0.06
    Act Density 0.015%

    No Known Activations