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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     correspond
    -0.07
     Celtics
    -0.07
     patrol
    -0.07
    ован
    -0.06
    ificantly
    -0.06
     Eve
    -0.06
     McK
    -0.06
     από
    -0.06
     selecting
    -0.06
     dracon
    -0.06
    POSITIVE LOGITS
    굴
    0.07
     cái
    0.06
     [-
    0.06
    心理
    0.06
    "{
    0.06
    .cast
    0.06
    (gui
    0.06
    _fa
    0.06
    姊
    0.06
     Sinn
    0.05
    Act Density 0.013%

    No Known Activations