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

    Neuronpedia

    INDEX
    Explanations

    email addresses and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Overlay
    -0.07
    ف
    -0.07
    nam
    -0.07
    |`↵
    -0.07
    Gas
    -0.07
     ],
↵
    -0.06
    Bob
    -0.06
     city
    -0.06
    notif
    -0.06
    (milliseconds
    -0.06
    POSITIVE LOGITS
     Пав
    0.07
    _indices
    0.07
     كرد
    0.07
    (wallet
    0.06
    .scalatest
    0.06
     perfected
    0.06
    (css
    0.06
    '][$
    0.06
    Existing
    0.06
    А
    0.06
    Act Density 0.033%

    No Known Activations