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

    Neuronpedia

    INDEX
    Explanations

    Discrepancies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ton
    -0.07
     Appe
    -0.07
     attorneys
    -0.06
     residential
    -0.06
    Man
    -0.06
     ní
    -0.06
    -svg
    -0.06
     Agents
    -0.06
     derecho
    -0.06
     Violence
    -0.06
    POSITIVE LOGITS
    =''↵
    0.06
    UPI
    0.06
     assessing
    0.06
     dm
    0.06
     фев
    0.06
     ألف
    0.06
    ubit
    0.06
    _QMARK
    0.06
    .environ
    0.06
    &&&&
    0.06
    Act Density 0.230%

    No Known Activations