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

    Neuronpedia

    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.08
    选取
    -0.08
     uses
    -0.07
     eldre
    -0.07
     lay
    -0.07
    енных
    -0.06
    所述
    -0.06
    研究生
    -0.06
     audits
    -0.06
     press
    -0.06
    POSITIVE LOGITS
    .CompareTag
    0.07
    kı
    0.07
    一万
    0.07
     GW
    0.07
     vanity
    0.07
    (container
    0.07
    CAR
    0.07
     contour
    0.07
     Sag
    0.06
     BAM
    0.06
    Act Density 0.299%

    No Known Activations