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

    Neuronpedia

    INDEX
    Explanations

    brackets and code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nothing
    -0.07
    .Pool
    -0.06
    _lift
    -0.06
    AMAGE
    -0.06
     Closet
    -0.06
     LINK
    -0.06
     Panthers
    -0.06
    Expect
    -0.06
     directed
    -0.06
     Captain
    -0.06
    POSITIVE LOGITS
    .Euler
    0.06
    orElse
    0.06
    另外
    0.06
     insult
    0.06
    ีด
    0.06
    SURE
    0.06
     }
↵
↵
↵
    0.06
    ernote
    0.06
     */↵↵↵↵
    0.06
    putc
    0.06
    Act Density 0.017%

    No Known Activations