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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibilidade
    -0.08
     kids
    -0.07
     sanctuary
    -0.06
     Li
    -0.06
     Cheng
    -0.06
    ény
    -0.06
    ko
    -0.06
    ackets
    -0.06
     fighter
    -0.06
     Speakers
    -0.06
    POSITIVE LOGITS
    DEFINED
    0.06
    	draw
    0.06
    phies
    0.06
    OGLE
    0.06
     insol
    0.06
     */
↵
↵
    0.06
    イン
    0.06
    	gl
    0.06
     //}↵↵
    0.06
     OpCode
    0.06
    Act Density 0.009%

    No Known Activations