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

    Neuronpedia

    INDEX
    Explanations

    design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    莫
    -0.07
    .LENGTH
    -0.07
    (common
    -0.07
     γνω
    -0.07
     şeklinde
    -0.06
    .Save
    -0.06
     تم
    -0.06
    “There
    -0.06
    _stage
    -0.06
     kennen
    -0.06
    POSITIVE LOGITS
     Design
    0.07
     fabrication
    0.06
    regn
    0.06
     Vor
    0.06
     Zus
    0.06
     Wyatt
    0.06
    .validation
    0.06
     Diesel
    0.06
    ffer
    0.06
     hiệu
    0.06
    Act Density 0.010%

    No Known Activations