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

    Neuronpedia

    INDEX
    Explanations

    Court cases and legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qualitative
    -0.07
    _LL
    -0.07
     Islamist
    -0.07
    Seeder
    -0.07
    حج
    -0.07
    民主
    -0.07
     ascertain
    -0.06
    videos
    -0.06
    ʧ
    -0.06
    Zoom
    -0.06
    POSITIVE LOGITS
     worker
    0.07
     presentation
    0.07
     rotation
    0.07
     poster
    0.07
    vio
    0.07
    ORK
    0.07
    ✭
    0.07
     here
    0.07
    LOCK
    0.07
    บรรยาก
    0.06
    Act Density 0.020%

    No Known Activations