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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    noticed
    -0.07
    .gz
    -0.06
     unhappy
    -0.06
     Gro
    -0.06
    Cool
    -0.06
    /'+
    -0.06
     Jas
    -0.06
    zv
    -0.06
     Basel
    -0.06
     Preis
    -0.06
    POSITIVE LOGITS
    .SelectCommand
    0.07
    .listeners
    0.06
    	Rect
    0.06
     oran
    0.06
     classmates
    0.06
    ();
↵
↵
    0.06
     shoots
    0.06
    leccion
    0.06
     Departments
    0.06
     purchases
    0.06
    Act Density 0.001%

    No Known Activations