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

    Neuronpedia

    INDEX
    Explanations

    relative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     solicitud
    -0.07
    _logical
    -0.07
     minutes
    -0.07
     graduate
    -0.07
     haul
    -0.06
     nueva
    -0.06
    اجات
    -0.06
     přiv
    -0.06
     slave
    -0.06
     Dawn
    -0.06
    POSITIVE LOGITS
    tuğ
    0.07
     %=
    0.07
    حي
    0.06
    <bits
    0.06
     نرم
    0.06
     پیشنهاد
    0.06
    ความ
    0.06
    <_
    0.06
    orta
    0.06
     undecided
    0.06
    Act Density 0.005%

    No Known Activations