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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Resource
    -0.07
    .extension
    -0.07
     Choices
    -0.07
     праців
    -0.06
    .K
    -0.06
    CAT
    -0.06
    .Query
    -0.06
    held
    -0.06
    significant
    -0.06
    enade
    -0.06
    POSITIVE LOGITS
    _mov
    0.06
     stojí
    0.06
     paced
    0.06
    ierten
    0.06
    стри
    0.06
    '){
↵
    0.06
    ＞
    0.06
    ます
    0.06
     özellik
    0.06
     wished
    0.06
    Act Density 0.022%

    No Known Activations