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
     nicknamed
    -0.07
     напрям
    -0.07
    _dispatch
    -0.06
     mayo
    -0.06
     Latest
    -0.06
     ขาย
    -0.06
    andReturn
    -0.06
    ฐ
    -0.06
     Southern
    -0.06
     AssertionError
    -0.06
    POSITIVE LOGITS
    .http
    0.07
     Phelps
    0.06
    onation
    0.06
    __,
    0.06
    ΙΚΗ
    0.06
     undesirable
    0.06
     boob
    0.06
    rys
    0.06
     teaser
    0.06
    offs
    0.06
    Act Density 0.000%

    No Known Activations