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

    Neuronpedia

    INDEX
    Explanations

    computer science/mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    少儿
    -0.07
     phi
    -0.07
     לט
    -0.07
     untranslated
    -0.07
     RouterModule
    -0.07
    sessionId
    -0.07
    的投资
    -0.06
    queueReusableCell
    -0.06
     program
    -0.06
    .logged
    -0.06
    POSITIVE LOGITS
    arriv
    0.07
    яв
    0.07
     Beet
    0.07
    ارد
    0.07
    بق
    0.07
    总共
    0.07
    cap
    0.07
    лиц
    0.07
     Wolves
    0.06
    共
    0.06
    Act Density 0.012%

    No Known Activations