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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     databases
    -0.07
    Protocol
    -0.06
    лением
    -0.06
    ビ
    -0.06
     agencies
    -0.06
    'int
    -0.06
     rugged
    -0.06
    くん
    -0.06
    	dialog
    -0.06
    来た
    -0.06
    POSITIVE LOGITS
     وت
    0.07
    '"↵
    0.06
    %^
    0.06
     cancelButton
    0.06
     ✓
    0.06
    ="">
↵
    0.06
    ,$_
    0.06
    ="<?=
    0.06
    .amazon
    0.06
    ","",
    0.06
    Act Density 0.032%

    No Known Activations