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
     mindfulness
    -0.07
     rand
    -0.07
    城市
    -0.06
    antes
    -0.06
     ','
    -0.06
    zem
    -0.06
     liberated
    -0.06
    ラ
    -0.06
     Structural
    -0.06
    asser
    -0.06
    POSITIVE LOGITS
    两人
    0.08
     Wolver
    0.07
    あの
    0.07
     機
    0.06
     حکم
    0.06
    .Any
    0.06
     mainWindow
    0.06
    -extension
    0.06
     اداره
    0.06
     Finals
    0.06
    Act Density 0.002%

    No Known Activations