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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nails
    -0.07
    ================================================
    -0.07
    Permissions
    -0.06
    	X
    -0.06
    	Game
    -0.06
     catalog
    -0.06
     Hội
    -0.06
    (fm
    -0.06
     usher
    -0.06
    -services
    -0.06
    POSITIVE LOGITS
     pdo
    0.07
     आई
    0.06
     weakSelf
    0.06
     Wichita
    0.06
    _inds
    0.06
    scrollView
    0.06
    /unit
    0.06
    적으로
    0.06
    CASCADE
    0.06
     localVar
    0.06
    Act Density 0.008%

    No Known Activations