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
    jay
    -0.07
     park
    -0.06
    tmp
    -0.06
    .Position
    -0.06
     jag
    -0.06
     GCC
    -0.06
    ڰ
    -0.06
     [],
↵
    -0.06
    _traffic
    -0.06
    kid
    -0.06
    POSITIVE LOGITS
    .SH
    0.07
     cookies
    0.07
    -S
    0.07
     в
    0.07
    TestCase
    0.07
    Friday
    0.07
    accounts
    0.07
     measured
    0.07
     Clears
    0.07
    astery
    0.06
    Act Density 0.062%

    No Known Activations