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

    Neuronpedia

    INDEX
    Explanations

    hyphens and associated nearby characters.

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.85
    -
    -0.81
     propOrder
    -0.68
     pinulongan
    -0.66
    رشف
    -0.61
    EndContext
    -0.61
     EconPapers
    -0.60
    новништво
    -0.60
    setVerticalGroup
    -0.60
    quiao
    -0.59
    POSITIVE LOGITS
    arci
    0.50
    aronder
    0.50
    .}~\
    0.49
     פני
    0.48
     DÍA
    0.47
    olytic
    0.47
    massen
    0.46
    izes
    0.45
    pirable
    0.45
    heim
    0.44
    Act Density 6.155%

    No Known Activations