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

    Neuronpedia

    INDEX
    Explanations

    made

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.08
    Arrange
    -0.07
    **↵
    -0.07
     Princess
    -0.06
    arnation
    -0.06
    �
    -0.06
    -filter
    -0.06
    .Experimental
    -0.06
    ัน
    -0.06
    ‌پدی
    -0.06
    POSITIVE LOGITS
    ระหว
    0.07
    @testable
    0.06
    \xff
    0.06
    ivet
    0.06
    IBOutlet
    0.06
     başvur
    0.06
    401
    0.06
    음
    0.06
     sebe
    0.06
    (con
    0.06
    Act Density 0.001%

    No Known Activations