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

    Neuronpedia

    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (DB
    -0.07
     เมษายน
    -0.06
    layarak
    -0.06
     اولیه
    -0.06
    .Cloud
    -0.06
     dưới
    -0.06
    (ticket
    -0.06
    .Value
    -0.06
    >]
    -0.06
     walker
    -0.06
    POSITIVE LOGITS
     USPS
    0.08
    vail
    0.07
    istream
    0.06
    TexParameter
    0.06
     demographics
    0.06
    credible
    0.06
    _encrypt
    0.06
     Psalm
    0.06
    /item
    0.06
    chied
    0.06
    Act Density 0.014%

    No Known Activations