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

    Neuronpedia

    INDEX
    Explanations

    Company office locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Turning
    -0.07
     Leg
    -0.07
    辜负
    -0.07
    般的
    -0.07
    木材
    -0.07
    翡
    -0.07
     metals
    -0.07
    我去
    -0.07
    鲧
    -0.07
    嫣
    -0.07
    POSITIVE LOGITS
     SECURITY
    0.07
    language
    0.07
    schedule
    0.07
     contains
    0.07
    buy
    0.07
    	duration
    0.06
     existence
    0.06
     penalty
    0.06
     belt
    0.06
    عش
    0.06
    Act Density 0.031%

    No Known Activations