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

    Neuronpedia

    INDEX
    Explanations

    sentence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uplift
    -0.07
    <ul
    -0.06
     Pattern
    -0.06
    um
    -0.06
    	Array
    -0.06
     групи
    -0.06
     نو
    -0.06
    ับสน
    -0.06
     Confidence
    -0.06
     computations
    -0.06
    POSITIVE LOGITS
    hots
    0.07
    InThe
    0.07
    ibBundleOrNil
    0.07
    illage
    0.06
     showc
    0.06
    issions
    0.06
     Unt
    0.06
     disclosures
    0.06
    $MESS
    0.06
     isEmpty
    0.06
    Act Density 0.017%

    No Known Activations