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

    Neuronpedia

    INDEX
    Explanations

    document excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Minimum
    -0.08
     BM
    -0.08
     combien
    -0.08
    BM
    -0.08
     fascia
    -0.08
     прор
    -0.07
     rectangles
    -0.07
     skup
    -0.07
    рина
    -0.07
     сколько
    -0.07
    POSITIVE LOGITS
     Island
    0.15
     island
    0.15
     Islands
    0.14
    岛
    0.14
     islands
    0.14
    島
    0.13
    Island
    0.13
     Islanders
    0.12
    'île
    0.12
     eiland
    0.12
    Act Density 0.073%

    No Known Activations