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

    Neuronpedia

    INDEX
    Explanations

    mathematical problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FL
    -0.08
     несмотря
    -0.08
     knit
    -0.08
    ائل
    -0.08
    _Base
    -0.08
    ни
    -0.08
     neemt
    -0.08
    ​ធ
    -0.08
     получается
    -0.08
    .stdout
    -0.08
    POSITIVE LOGITS
     criteria
    0.14
     Kriterien
    0.13
     Criteria
    0.13
     criterion
    0.12
     critérios
    0.12
     Criterion
    0.11
    criteria
    0.11
    .criteria
    0.11
    Criteria
    0.11
    Criterion
    0.11
    Act Density 0.076%

    No Known Activations