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

    Neuronpedia

    INDEX
    Explanations

    experts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     else's
    -0.08
    ringen
    -0.08
     stringify
    -0.08
    idikan
    -0.08
    Histogram
    -0.08
    是多少
    -0.08
    constraint
    -0.08
    Songs
    -0.08
     PERFORMANCE
    -0.07
    constraints
    -0.07
    POSITIVE LOGITS
     experts
    0.19
     analysts
    0.18
     специалисты
    0.18
     professionals
    0.18
    负责人
    0.18
    人士
    0.18
     специалист
    0.17
    专家
    0.17
    工作人员
    0.17
     researchers
    0.17
    Act Density 0.373%

    No Known Activations