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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -prop
    -0.07
    이드
    -0.07
    utra
    -0.07
    .The
    -0.06
    ckeditor
    -0.06
    вед
    -0.06
     Receive
    -0.06
    ")}
    -0.06
    Yang
    -0.06
    -pro
    -0.06
    POSITIVE LOGITS
     Gerard
    0.07
    [Y
    0.06
     tubing
    0.06
     정말
    0.06
    ->[
    0.06
    (man
    0.06
     Burton
    0.06
     cerv
    0.06
    (expression
    0.06
     kW
    0.06
    Act Density 0.227%

    No Known Activations