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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    624
    -0.07
    дем
    -0.07
    raphic
    -0.07
    	stmt
    -0.07
    alon
    -0.06
     查
    -0.06
    rob
    -0.06
    lack
    -0.06
    الث
    -0.06
    <|end_of_text|>
    -0.06
    POSITIVE LOGITS
    NotNull
    0.06
     hikes
    0.06
     대한민국
    0.06
    Evaluate
    0.06
    =models
    0.06
     Ал
    0.06
     CLIIIK
    0.06
     Writing
    0.06
    -owned
    0.06
     maximizing
    0.06
    Act Density 0.031%

    No Known Activations