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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	height
    -0.07
    -policy
    -0.07
     authorization
    -0.07
    -health
    -0.07
     Editors
    -0.06
     travers
    -0.06
    _dimensions
    -0.06
     withdrawal
    -0.06
     acquisition
    -0.06
     LLC
    -0.06
    POSITIVE LOGITS
    ΜΠ
    0.07
    base
    0.06
    坡
    0.06
     paar
    0.06
    ece
    0.06
    \App
    0.06
    .Exists
    0.06
    本
    0.06
    ButtonType
    0.06
    .JOptionPane
    0.06
    Act Density 0.015%

    No Known Activations