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

    Neuronpedia

    INDEX
    Explanations

    parenthesis and/or semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sama
    -0.07
     بش
    -0.06
     boosted
    -0.06
    .review
    -0.06
     буду
    -0.06
    نين
    -0.06
    ضاء
    -0.06
    Choices
    -0.06
    |^
    -0.06
    Boston
    -0.06
    POSITIVE LOGITS
     spiders
    0.07
    --------------------------------------------------------------------------↵
    0.07
     instincts
    0.06
     franç
    0.06
     kıl
    0.06
     рук
    0.06
     handwriting
    0.06
     francaise
    0.06
     MatDialog
    0.06
    countries
    0.06
    Act Density 0.162%

    No Known Activations