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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /download
    -0.06
     Multiply
    -0.06
    _footer
    -0.06
    _square
    -0.06
     cup
    -0.06
    ัคร
    -0.06
     мы
    -0.06
    .UP
    -0.06
     judicial
    -0.06
    (Project
    -0.06
    POSITIVE LOGITS
    illard
    0.07
    erse
    0.07
    álo
    0.06
     území
    0.06
    _prediction
    0.06
     behand
    0.06
    existing
    0.06
     slowed
    0.06
    ardin
    0.06
     appearances
    0.06
    Act Density 0.011%

    No Known Activations