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

    Neuronpedia

    INDEX
    Explanations

    First-person narrative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    akit
    -0.06
     grunt
    -0.06
    mites
    -0.06
    μά
    -0.06
     conveniently
    -0.06
     Roe
    -0.06
    .Components
    -0.06
    'A
    -0.06
    خی
    -0.06
    (pow
    -0.06
    POSITIVE LOGITS
    (payment
    0.08
    opyright
    0.07
     probing
    0.07
     analy
    0.07
     Period
    0.07
     webs
    0.07
     appl
    0.06
     gate
    0.06
    _FLAGS
    0.06
     arbe
    0.06
    Act Density 0.039%

    No Known Activations