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

    Neuronpedia

    INDEX
    Explanations

    Web addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yıl
    -0.07
    (trigger
    -0.07
    (signature
    -0.07
     MK
    -0.06
    Translatef
    -0.06
    talk
    -0.06
     module
    -0.06
    وسط
    -0.06
    _STATUS
    -0.06
     Guards
    -0.06
    POSITIVE LOGITS
     учрежд
    0.06
    sure
    0.06
     agr
    0.06
     pace
    0.06
    ослав
    0.06
     Beh
    0.06
    hower
    0.06
    VER
    0.06
     او
    0.06
    chein
    0.06
    Act Density 0.021%

    No Known Activations