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

    Neuronpedia

    INDEX
    Explanations

    code and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rand
    -0.07
    реж
    -0.06
     KC
    -0.06
    (left
    -0.06
     det
    -0.06
    Certain
    -0.06
    cbd
    -0.06
    loat
    -0.06
    开
    -0.06
     aden
    -0.06
    POSITIVE LOGITS
    upaten
    0.07
    _CRYPTO
    0.07
     duygu
    0.07
     التف
    0.06
    _sources
    0.06
     центр
    0.06
    微
    0.06
     dolayı
    0.06
     hvordan
    0.06
    (car
    0.06
    Act Density 0.220%

    No Known Activations