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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	editor
    -0.08
    .Publish
    -0.07
     securities
    -0.07
    ♱
    -0.07
     messageId
    -0.07
    ersive
    -0.07
     getLast
    -0.07
    isen
    -0.07
     editor
    -0.07
    法律
    -0.07
    POSITIVE LOGITS
    .Roll
    0.07
    圆
    0.07
    ფ
    0.07
    պ
    0.07
    .o
    0.07
    BBBB
    0.07
    .ov
    0.07
    本身就是
    0.07
    .company
    0.07
     TokenType
    0.06
    Act Density 0.012%

    No Known Activations