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

    Neuronpedia

    INDEX
    Explanations

    Character names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KG
    -0.07
    صح
    -0.07
    Queen
    -0.07
    -0.06
    -0.06
    ینک
    -0.06
    queen
    -0.06
    quee
    -0.06
    _clicked
    -0.06
     cultivate
    -0.06
    POSITIVE LOGITS
    监听页面
    0.07
    .surface
    0.07
    toMatch
    0.07
     volta
    0.07
    .RowIndex
    0.07
    .normalize
    0.06
    .setContentType
    0.06
    ihilation
    0.06
    (policy
    0.06
     Laos
    0.06
    Act Density 0.035%

    No Known Activations