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

    Neuronpedia

    INDEX
    Explanations

    References and external links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endtime
    -0.06
    دد
    -0.06
     Gap
    -0.06
    ück
    -0.06
    ارهای
    -0.06
    驗
    -0.06
    _msg
    -0.06
    rün
    -0.06
     نظامی
    -0.06
    (spec
    -0.06
    POSITIVE LOGITS
    Е
    0.07
    -generation
    0.06
     peace
    0.06
    ureen
    0.06
     Officers
    0.06
    hours
    0.06
     *)↵↵
    0.06
     column
    0.06
     Proof
    0.06
     emotions
    0.06
    Act Density 0.026%

    No Known Activations