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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    minute
    -0.07
     mate
    -0.06
     mog
    -0.06
     epoch
    -0.06
     succès
    -0.06
    _TREE
    -0.06
     MAG
    -0.06
     EVENT
    -0.06
    _stack
    -0.06
    Email
    -0.06
    POSITIVE LOGITS
     Explicit
    0.06
    Expected
    0.06
    τιο
    0.06
    ////↵
    0.06
    	SP
    0.06
    /↵↵↵↵
    0.06
    			 ↵
    0.06
    	bg
    0.06
     glColor
    0.06
    ----------
↵
    0.06
    Act Density 0.004%

    No Known Activations