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

    Neuronpedia

    INDEX
    Explanations

    single

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dönem
    -0.07
     Ave
    -0.06
     Avenue
    -0.06
    _break
    -0.06
    billing
    -0.06
    ازل
    -0.06
     beaches
    -0.06
     Drinks
    -0.06
    Rights
    -0.06
     замі
    -0.06
    POSITIVE LOGITS
    >NN
    0.07
     Garten
    0.07
    Emma
    0.06
    凌
    0.06
    Scalar
    0.06
     şer
    0.06
    भग
    0.06
    oute
    0.06
    ΥΣ
    0.06
     اص
    0.06
    Act Density 0.008%

    No Known Activations