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

    Neuronpedia

    INDEX
    Explanations

    professional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dort
    -0.07
    孕期
    -0.07
     Reverse
    -0.07
     pencil
    -0.06
    Traversal
    -0.06
    ard
    -0.06
    EDIUM
    -0.06
     lässt
    -0.06
     ResourceType
    -0.06
     Pepper
    -0.06
    POSITIVE LOGITS
     polit
    0.08
    该怎么办
    0.08
    (KP
    0.07
     banking
    0.07
    .fire
    0.07
    高尚
    0.07
    讲故事
    0.07
     chấp
    0.06
    VALUES
    0.06
    _ru
    0.06
    Act Density 0.065%

    No Known Activations