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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    creasing
    -0.07
    icted
    -0.07
    Cd
    -0.07
    _Font
    -0.06
    ERICA
    -0.06
     ChatColor
    -0.06
    Vehicle
    -0.06
    BarItem
    -0.06
    Handling
    -0.06
    Snake
    -0.06
    POSITIVE LOGITS
     polym
    0.07
    meldung
    0.07
     Essentially
    0.06
    	reset
    0.06
    92
    0.06
    -btn
    0.06
     оди
    0.06
     cis
    0.06
    SAFE
    0.06
     Bool
    0.06
    Act Density 0.024%

    No Known Activations