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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    校
    -0.07
    Martin
    -0.07
     Martin
    -0.06
     pen
    -0.06
    Report
    -0.06
    เหมาะ
    -0.06
    experience
    -0.06
    ara
    -0.06
     Governments
    -0.06
     kısm
    -0.06
    POSITIVE LOGITS
    นาง
    0.07
     "~/
    0.07
     =============================================================================↵
    0.06
    references
    0.06
     cose
    0.06
    (\$
    0.06
    Entering
    0.06
     Explicit
    0.06
    �
    0.06
    аного
    0.06
    Act Density 0.006%

    No Known Activations