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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lazy
    -0.07
     truck
    -0.07
     Thai
    -0.07
     redo
    -0.06
     Sofa
    -0.06
     Sus
    -0.06
     Zeus
    -0.06
     comics
    -0.06
     �
    -0.06
    todos
    -0.06
    POSITIVE LOGITS
    [cur
    0.07
    [B
    0.06
    /************************************************************************
    0.06
    (priv
    0.06
     unfolded
    0.06
     доз
    0.06
     داد
    0.06
     UIKit
    0.06
    RR
    0.06
    PopMatrix
    0.06
    Act Density 0.064%

    No Known Activations