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

    Neuronpedia

    INDEX
    Explanations

    ///

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frente
    -0.07
    呗
    -0.07
     dez
    -0.07
    endet
    -0.07
     conocer
    -0.07
    的道路
    -0.07
     cường
    -0.07
     çeş
    -0.07
    ࠍ
    -0.06
    ://"
    -0.06
    POSITIVE LOGITS
    Agents
    0.07
    district
    0.07
    (li
    0.07
    area
    0.07
    补贴
    0.07
    薪水
    0.07
     qa
    0.07
    Classifier
    0.06
    .prob
    0.06
    𝑋
    0.06
    Act Density 0.006%

    No Known Activations