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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !
    -0.07
    ‌خ
    -0.07
     forKey
    -0.07
     leftist
    -0.07
    )][
    -0.07
     الثالث
    -0.07
     []
    -0.07
    _track
    -0.06
     {\
    -0.06
     disconnect
    -0.06
    POSITIVE LOGITS
    colour
    0.07
     Protestant
    0.07
    ौ
    0.07
     très
    0.06
     عصر
    0.06
     проте
    0.06
    Simply
    0.06
    ushman
    0.06
    oucher
    0.05
    olini
    0.05
    Act Density 0.105%

    No Known Activations