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

    Neuronpedia

    INDEX
    Explanations

    book introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bserv
    -0.07
    ادن
    -0.06
     язы
    -0.06
    Topic
    -0.06
    onds
    -0.06
     performer
    -0.06
     кот
    -0.06
    Grade
    -0.06
     case
    -0.06
     Rugby
    -0.06
    POSITIVE LOGITS
    enství
    0.07
    nested
    0.07
     mappedBy
    0.07
    нист
    0.06
    .Sm
    0.06
    _ACTIVE
    0.06
    Рµ
    0.06
    Additionally
    0.06
     demir
    0.06
     altered
    0.06
    Act Density 0.007%

    No Known Activations