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

    Neuronpedia

    INDEX
    Explanations

    energy efficiency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Adjust
    -0.07
    \P
    -0.07
    重点
    -0.07
     Accordingly
    -0.06
    221
    -0.06
    Lifetime
    -0.06
    ACCESS
    -0.06
     aggregates
    -0.06
     Floating
    -0.06
    ROUTE
    -0.06
    POSITIVE LOGITS
     chant
    0.07
     chants
    0.06
    _product
    0.06
     Found
    0.06
     applicant
    0.06
     Exercises
    0.06
     downt
    0.05
    олет
    0.05
    ْع
    0.05
     }}"↵
    0.05
    Act Density 0.036%

    No Known Activations