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
     bilateral
    -0.07
     Bios
    -0.06
     dynasty
    -0.06
    odynam
    -0.06
    iever
    -0.06
     Premi
    -0.06
    θεση
    -0.06
    ycling
    -0.06
    .Delete
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    exceptions
    0.08
    <\/
    0.07
    ):
    0.07
    νομα
    0.07
     �
    0.06
    ################################################################################
    0.06
    _-
    0.06
     продолж
    0.06
     splendid
    0.06
    ivě
    0.06
    Act Density 0.006%

    No Known Activations