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

    Neuronpedia

    INDEX
    Explanations

    a/an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     veri
    -0.07
     ant
    -0.07
     Racing
    -0.06
     рук
    -0.06
     cosplay
    -0.06
    .junit
    -0.06
     Zodiac
    -0.06
    Tony
    -0.06
     controvers
    -0.06
     ribbon
    -0.06
    POSITIVE LOGITS
     يم
    0.07
    حاد
    0.07
    ้อย
    0.06
    กล
    0.06
    λό
    0.06
    flatten
    0.06
    UIApplication
    0.06
    적으로
    0.06
     стоимость
    0.06
    _trajectory
    0.06
    Act Density 0.041%

    No Known Activations