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

    Neuronpedia

    INDEX
    Explanations

    Snippets of text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    463
    -0.07
    onas
    -0.06
     dum
    -0.06
     Sawyer
    -0.06
     Reed
    -0.06
    到
    -0.06
     charter
    -0.06
     warehouse
    -0.06
    _irq
    -0.06
    ToSend
    -0.06
    POSITIVE LOGITS
    aab
    0.07
    "]))
    0.07
    ichTextBox
    0.06
    Bounding
    0.06
     UITextView
    0.06
     hectic
    0.06
    рой
    0.06
    正常
    0.06
    ạch
    0.06
    !!}</
    0.06
    Act Density 0.191%

    No Known Activations