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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CODE
    -0.06
    	x
    -0.06
    ペ
    -0.06
     vua
    -0.06
    庭
    -0.06
    Ag
    -0.06
     preferably
    -0.06
    ик
    -0.06
    	C
    -0.06
    ाइव
    -0.06
    POSITIVE LOGITS
    Hints
    0.07
    .Header
    0.07
     criticized
    0.06
    .swagger
    0.06
    SearchParams
    0.06
     Ether
    0.06
    Va
    0.06
     pillows
    0.06
    Matches
    0.06
    taş
    0.06
    Act Density 0.039%

    No Known Activations