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

    Neuronpedia

    INDEX
    Explanations

    punctuations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .key
    -0.07
    �
    -0.07
    getConfig
    -0.07
    ara
    -0.07
     hepatitis
    -0.07
    Cele
    -0.06
    _accum
    -0.06
    SearchParams
    -0.06
    =headers
    -0.06
    $options
    -0.06
    POSITIVE LOGITS
     Charger
    0.07
     Blaze
    0.07
     Gerald
    0.07
     phận
    0.07
     appearance
    0.07
     WTO
    0.07
    物种
    0.06
     Yap
    0.06
    Game
    0.06
     teammate
    0.06
    Act Density 0.052%

    No Known Activations