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

    Neuronpedia

    INDEX
    Explanations

    negative events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     解
    -0.07
     étaient
    -0.07
    .reduce
    -0.06
    scenario
    -0.06
     Delhi
    -0.06
    _listing
    -0.06
     silky
    -0.06
    "A
    -0.06
    ,**
    -0.06
    .active
    -0.06
    POSITIVE LOGITS
     движения
    0.07
    HG
    0.06
     deeply
    0.06
    وجه
    0.06
    tection
    0.06
    Driven
    0.06
     percussion
    0.06
     structural
    0.06
    resident
    0.06
     Rug
    0.06
    Act Density 0.008%

    No Known Activations