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

    Neuronpedia

    INDEX
    Explanations

    empty or errors in code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     -----↵
    -0.08
    meye
    -0.07
    %");↵
    -0.07
    vary
    -0.06
    构
    -0.06
     Suites
    -0.06
    (Yii
    -0.06
     Gamma
    -0.06
    計劃
    -0.06
     pod
    -0.06
    POSITIVE LOGITS
    estation
    0.06
    .Up
    0.06
     Hog
    0.06
     Wolver
    0.06
    抓
    0.06
     Siri
    0.06
     ip
    0.06
    athroom
    0.06
     consul
    0.06
    _IMPORT
    0.06
    Act Density 0.071%

    No Known Activations