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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gate
    -0.07
    umble
    -0.07
    ог
    -0.06
     IRS
    -0.06
    ouble
    -0.06
    ulance
    -0.06
     flames
    -0.06
     occupancy
    -0.06
     serpent
    -0.06
     UPS
    -0.06
    POSITIVE LOGITS
     �
    0.07
     прибор
    0.07
    anie
    0.06
    default
    0.06
    .ie
    0.06
    加入
    0.06
     pine
    0.06
     risky
    0.06
     منه
    0.06
     ایشان
    0.06
    Act Density 0.008%

    No Known Activations