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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    隨時
    -0.07
    hör
    -0.07
    冯
    -0.07
    aptor
    -0.07
     Attempts
    -0.07
     assertion
    -0.07
    襲
    -0.06
    .api
    -0.06
     pornôs
    -0.06
    应邀
    -0.06
    POSITIVE LOGITS
    	sys
    0.07
    .MONTH
    0.07
     DB
    0.07
    FileDialog
    0.07
    ml
    0.07
     Card
    0.07
     "_
    0.06
    .poi
    0.06
     CAL
    0.06
    太阳能
    0.06
    Act Density 0.118%

    No Known Activations