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

    Neuronpedia

    INDEX
    Explanations

    the word "binding", particularly in a technical context

    oai_token-act-pair · gemini-2.0-flash

    binding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.16
     Efq
    -1.14
     reaſon
    -1.07
     Majefty
    -1.06
     faſt
    -1.05
     myſelf
    -1.02
     poffible
    -1.02
     Diſ
    -1.02
     becauſe
    -1.01
     raiſ
    -1.01
    POSITIVE LOGITS
    ly
    0.75
    ,
    0.72
    .
    0.68
    y
    0.68
    line
    0.65
    s
    0.65
    for
    0.60
    :
    0.58
    com
    0.56
    ся
    0.55
    Act Density 0.516%

    No Known Activations