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

    Neuronpedia

    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bumped
    -0.06
    Main
    -0.06
     některé
    -0.06
     time
    -0.06
    online
    -0.06
    reeting
    -0.06
     cocaine
    -0.06
    ıcı
    -0.06
    (default
    -0.06
    .square
    -0.06
    POSITIVE LOGITS
     Boca
    0.07
    град
    0.07
     Physician
    0.06
    nr
    0.06
    234
    0.06
    ENTE
    0.06
     untouched
    0.06
     över
    0.06
     Werner
    0.06
    grab
    0.06
    Act Density 0.005%

    No Known Activations