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

    Neuronpedia

    INDEX
    Explanations

    head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Assign
    -0.09
    -0.08
    .APP
    -0.07
     Florence
    -0.07
    宮
    -0.07
    offee
    -0.07
    LOOP
    -0.07
    .Skip
    -0.07
     apoptosis
    -0.06
    ASE
    -0.06
    POSITIVE LOGITS
    فارق
    0.07
    NSURL
    0.07
    tic
    0.06
    ourke
    0.06
     area
    0.06
     stocking
    0.06
     Atari
    0.06
     başlat
    0.06
     właśc
    0.06
    ö
    0.06
    Act Density 0.015%

    No Known Activations