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

    Neuronpedia

    INDEX
    Explanations

    capture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encyclopedia
    -0.09
     cad
    -0.08
     cél
    -0.08
    Division
    -0.08
     toh
    -0.08
    вед
    -0.08
     жест
    -0.08
     faithful
    -0.07
     profundidad
    -0.07
     hafta
    -0.07
    POSITIVE LOGITS
     Technologien
    0.12
     technologies
    0.11
     greenhouse
    0.10
    设施
    0.10
    技术
    0.10
     технологий
    0.09
     Facilities
    0.09
     Facility
    0.09
     தொழ
    0.09
    措施
    0.09
    Act Density 0.001%

    No Known Activations