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

    Neuronpedia

    INDEX
    Explanations

    injections/shots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (urls
    -0.06
    ですが
    -0.06
    -0.06
     НА
    -0.06
     rush
    -0.06
     optarg
    -0.06
     dikkat
    -0.06
     tí
    -0.06
    isease
    -0.06
     nx
    -0.06
    POSITIVE LOGITS
     tick
    0.08
     Archer
    0.07
    stinian
    0.07
    cribed
    0.06
    .pay
    0.06
    �y
    0.06
     peanut
    0.06
     Extra
    0.06
     giorni
    0.06
    мон
    0.06
    Act Density 0.037%

    No Known Activations