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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gol
    -0.07
    .len
    -0.07
    Pair
    -0.06
     Names
    -0.06
     infect
    -0.06
     lovers
    -0.06
     suc
    -0.06
     να
    -0.06
     Bur
    -0.06
    	GL
    -0.06
    POSITIVE LOGITS
     oyn
    0.07
     승
    0.07
     sécur
    0.06
    brero
    0.06
     hinges
    0.06
     zoek
    0.06
     classical
    0.06
     treaties
    0.06
    /windows
    0.06
    _pagination
    0.06
    Act Density 0.005%

    No Known Activations