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

    Neuronpedia

    INDEX
    Explanations

    data type issues / arrays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    чу
    -0.08
     empowerment
    -0.08
     credito
    -0.08
     agua
    -0.08
    copyright
    -0.08
     devotion
    -0.08
     stewardship
    -0.07
     ọwọ
    -0.07
    METHOD
    -0.07
     PEOPLE
    -0.07
    POSITIVE LOGITS
    统一
    0.13
    Uniform
    0.10
     uniform
    0.10
     unify
    0.09
    uniform
    0.09
     homog
    0.09
     unified
    0.09
    .tight
    0.09
     Uniform
    0.09
    _uniform
    0.09
    Act Density 0.006%

    No Known Activations