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

    Neuronpedia

    INDEX
    Explanations

    someone working through a math problem and thinking out loud

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ushman
    -0.06
    ayne
    -0.06
     multiple
    -0.06
     divers
    -0.06
     illegal
    -0.06
    ä»»ä½ķ
    -0.06
    uchen
    -0.06
     cannot
    -0.06
     Impro
    -0.06
    937
    -0.05
    POSITIVE LOGITS
     beyond
    0.10
    eyond
    0.10
    Beyond
    0.09
     Beyond
    0.09
    ltre
    0.08
     continuation
    0.07
     checking
    0.07
    yonel
    0.07
     Checking
    0.07
     MetroFramework
    0.07
    Act Density 0.065%

    No Known Activations