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

    Neuronpedia

    INDEX
    Explanations

    Code/references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     устройства
    -0.07
    软
    -0.06
    qh
    -0.06
     prevents
    -0.06
     tossed
    -0.06
    mittel
    -0.06
    \Api
    -0.06
    reten
    -0.06
    .icon
    -0.06
     Comic
    -0.06
    POSITIVE LOGITS
     findAll
    0.07
     */↵↵↵
    0.06
    gression
    0.06
     servis
    0.06
    丝
    0.06
    ([('
    0.06
    _INFINITY
    0.06
    ỏ
    0.06
    _alert
    0.06
    ")↵↵↵
    0.06
    Act Density 0.181%

    No Known Activations