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

    Neuronpedia

    INDEX
    Explanations

    passages where someone is selecting between options

    oai_token-act-pair · gemini-2.0-flash

    choose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     choose
    -1.78
     Choose
    -1.57
    Choose
    -1.53
     chooses
    -1.50
    choose
    -1.50
     choosing
    -1.48
     chose
    -1.44
     Choosing
    -1.38
    Choosing
    -1.38
     CHOOSE
    -1.32
    POSITIVE LOGITS
    DoubleQuotes
    0.53
    ReusableCell
    0.47
    GOTREF
    0.46
    stdafx
    0.46
     resultMap
    0.45
     ")");
    0.44
     Gry
    0.43
     DRO
    0.43
     Dit
    0.43
    iprot
    0.43
    Act Density 8.622%

    No Known Activations