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

    Neuronpedia

    INDEX
    Explanations

    creation and customization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ार
    -0.07
     cancer
    -0.07
    Lin
    -0.06
     intrig
    -0.06
     vouchers
    -0.06
    Aceptar
    -0.06
     tester
    -0.06
     colleague
    -0.06
     <%
    -0.06
     koy
    -0.06
    POSITIVE LOGITS
     AVC
    0.07
    -ms
    0.06
    _hr
    0.06
    eventType
    0.06
     Oasis
    0.06
     Tweet
    0.06
    화를
    0.06
     *↵↵
    0.06
    0.06
     العملية
    0.06
    Act Density 0.309%

    No Known Activations