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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [start
    -0.07
     nen
    -0.07
    (pub
    -0.07
     endors
    -0.07
    wahl
    -0.07
    (pol
    -0.06
     adidas
    -0.06
    -add
    -0.06
    ("?
    -0.06
    urrenc
    -0.06
    POSITIVE LOGITS
     機
    0.08
     �
    0.07
     ره
    0.07
    ểm
    0.07
    :YES
    0.06
    альная
    0.06
    ?><?
    0.06
    قلال
    0.06
     QtCore
    0.06
     �
    0.06
    Act Density 0.028%

    No Known Activations