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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /menu
    -0.07
     fois
    -0.06
    imson
    -0.06
    Pink
    -0.06
    濃
    -0.06
     підпис
    -0.06
     ↵↵↵↵
    -0.05
     Sylvia
    -0.05
     onFinish
    -0.05
     biển
    -0.05
    POSITIVE LOGITS
    .background
    0.07
    -ranging
    0.07
    “At
    0.07
     arrang
    0.06
     usa
    0.06
    owner
    0.06
    _balance
    0.06
     exclusive
    0.06
     peel
    0.06
    [thread
    0.06
    Act Density 0.061%

    No Known Activations