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

    Neuronpedia

    INDEX
    Explanations

    Stage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TextArea
    -0.07
     ◑
    -0.07
    �
    -0.06
     meis
    -0.06
    Unfortunately
    -0.06
     Dip
    -0.06
     Perform
    -0.06
     ヾ
    -0.06
     volum
    -0.06
     carbon
    -0.06
    POSITIVE LOGITS
    /package
    0.07
    <Route
    0.07
    交通
    0.07
    .Frame
    0.06
    _Column
    0.06
    	context
    0.06
     route
    0.06
     soundtrack
    0.06
    NFL
    0.06
     (?,
    0.06
    Act Density 0.001%

    No Known Activations