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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blade
    -0.07
     inade
    -0.06
     دش
    -0.06
    .deltaTime
    -0.06
     watts
    -0.06
     гост
    -0.06
    _effects
    -0.06
    allet
    -0.06
    "How
    -0.06
    uggy
    -0.06
    POSITIVE LOGITS
    政治
    0.07
    853
    0.07
     discussion
    0.06
     컴
    0.06
     аг
    0.06
     وصل
    0.06
    BACK
    0.06
    �
    0.06
    _operator
    0.06
     dictionaryWith
    0.06
    Act Density 0.019%

    No Known Activations