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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _aspect
    -0.07
     cnt
    -0.07
    Specifications
    -0.07
     deutschen
    -0.07
     внешне
    -0.07
    BundleOrNil
    -0.06
     onze
    -0.06
     Franco
    -0.06
    .movie
    -0.06
     ni
    -0.06
    POSITIVE LOGITS
     doses
    0.09
     testData
    0.08
    目睹
    0.08
    蚯
    0.07
     correctness
    0.07
    暖气
    0.07
    紧迫
    0.07
     Mortgage
    0.07
    errorMessage
    0.07
     YEARS
    0.07
    Act Density 0.003%

    No Known Activations