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

    Neuronpedia

    INDEX
    Explanations

    technical writing samples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Canton
    -0.07
     cumshot
    -0.06
     nghị
    -0.06
     entend
    -0.06
     neger
    -0.06
    ξι
    -0.06
     DateTime
    -0.06
     raped
    -0.06
     фрукт
    -0.06
    蛛
    -0.06
    POSITIVE LOGITS
    .findViewById
    0.07
     Interestingly
    0.07
     Beginners
    0.06
     ELECT
    0.06
    ="'.
    0.06
    (signal
    0.06
    /back
    0.06
     negate
    0.06
     WikiLeaks
    0.06
     говорит
    0.06
    Act Density 0.205%

    No Known Activations