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

    Neuronpedia

    INDEX
    Explanations

    positive descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    леч
    -0.06
    ційно
    -0.06
    Think
    -0.06
     muit
    -0.06
    meter
    -0.06
     Transform
    -0.06
    킹
    -0.06
    典
    -0.06
     Require
    -0.06
     pert
    -0.06
    POSITIVE LOGITS
    _dense
    0.07
     containment
    0.06
    乎
    0.06
     pcl
    0.06
    recent
    0.06
     sağlıklı
    0.06
    urg
    0.06
    AML
    0.06
     potvr
    0.06
     basit
    0.06
    Act Density 0.182%

    No Known Activations