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

    Neuronpedia

    INDEX
    Explanations

    resolve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     projectId
    -0.07
     shuffled
    -0.07
    еж
    -0.07
     summarizes
    -0.06
    <Task
    -0.06
    -head
    -0.06
     slower
    -0.06
     zatím
    -0.06
     torch
    -0.06
    ٤
    -0.06
    POSITIVE LOGITS
     yeni
    0.07
     therapies
    0.06
    ヨ
    0.06
     هزینه
    0.06
     nephew
    0.06
     procedures
    0.06
     OnInit
    0.06
    TL
    0.06
    ісля
    0.06
     силь
    0.06
    Act Density 0.024%

    No Known Activations