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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dok
    -0.07
     לחל
    -0.07
     Applicant
    -0.07
     לחוק
    -0.07
    Ộ
    -0.06
    =document
    -0.06
    ournal
    -0.06
    신청
    -0.06
    东亚
    -0.06
     מצווה
    -0.06
    POSITIVE LOGITS
    潤
    0.07
    쑈
    0.07
     armor
    0.06
     avoided
    0.06
    ceeded
    0.06
    _accuracy
    0.06
     BaseService
    0.06
    pdb
    0.06
    verified
    0.06
     drought
    0.06
    Act Density 0.042%

    No Known Activations