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
     itm
    -0.06
    нин
    -0.06
    又
    -0.06
     ني
    -0.06
    .ButterKnife
    -0.06
    ../../../
    -0.06
    Inputs
    -0.06
     CHK
    -0.06
     Pediatric
    -0.06
     cn
    -0.06
    POSITIVE LOGITS
     위해서
    0.07
    PLE
    0.06
     INV
    0.06
    EXEC
    0.06
    orre
    0.06
    ÃO
    0.06
    .schedulers
    0.06
     prospective
    0.06
    %!
    0.06
    ão
    0.06
    Act Density 0.021%

    No Known Activations