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

    Neuronpedia

    INDEX
    Explanations

    legal, court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ~
    -0.07
     getString
    -0.06
    .take
    -0.06
     iterating
    -0.06
    broken
    -0.06
     screenings
    -0.06
    -growing
    -0.06
     PUT
    -0.06
     Som
    -0.06
     Adventures
    -0.06
    POSITIVE LOGITS
    CTION
    0.07
    (ai
    0.06
     Wildlife
    0.06
    /tool
    0.06
    assword
    0.06
    002
    0.06
    ijke
    0.06
    .getElementById
    0.06
    аль
    0.06
    _TC
    0.06
    Act Density 0.011%

    No Known Activations