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

    Neuronpedia

    INDEX
    Explanations

    websites and organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heg
    -0.08
    健康产业
    -0.07
    给自己
    -0.07
    .ff
    -0.07
    뭐
    -0.07
    民企
    -0.07
     targetType
    -0.07
    🔚
    -0.07
    走进
    -0.07
     necessarily
    -0.07
    POSITIVE LOGITS
     distra
    0.07
    MATCH
    0.07
    TU
    0.07
    thr
    0.07
    Italian
    0.07
    蓐
    0.07
     Boyd
    0.06
    _Update
    0.06
    rored
    0.06
    trys
    0.06
    Act Density 0.142%

    No Known Activations