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

    Neuronpedia

    INDEX
    Explanations

    resource and skill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seller
    -0.09
     centimeter
    -0.08
     öğren
    -0.08
     Behavior
    -0.08
    裂
    -0.08
     jailbreak
    -0.08
     байх
    -0.08
     penis
    -0.08
    ，坚持
    -0.07
    Seller
    -0.07
    POSITIVE LOGITS
    Assignments
    0.12
     staffing
    0.11
     realloc
    0.11
     manpower
    0.11
     assignments
    0.11
     workforce
    0.10
     Staffing
    0.10
     Workforce
    0.10
     allocated
    0.10
     idle
    0.10
    Act Density 0.019%

    No Known Activations