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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .assertFalse
    -0.08
     waive
    -0.07
    ullen
    -0.07
    ulação
    -0.07
    aine
    -0.07
    జ
    -0.07
    ILON
    -0.06
    一下子就
    -0.06
    :on
    -0.06
    了解一下
    -0.06
    POSITIVE LOGITS
    完美
    0.07
    arty
    0.07
    شك
    0.07
     наи
    0.07
    bes
    0.07
    QueryBuilder
    0.07
    פרד
    0.07
     Components
    0.07
    STE
    0.07
    螱
    0.07
    Act Density 0.065%

    No Known Activations