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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esity
    -0.06
     interpol
    -0.06
    Scott
    -0.06
     Appointment
    -0.06
     average
    -0.06
    720
    -0.06
     робот
    -0.06
    ικό
    -0.06
     '../../../../
    -0.05
    _Width
    -0.05
    POSITIVE LOGITS
     Solve
    0.07
     ».
    0.06
    année
    0.06
     eyes
    0.06
    σσα
    0.06
    _boost
    0.06
    weeks
    0.06
     wakes
    0.06
     Babe
    0.06
    .Repositories
    0.06
    Act Density 0.011%

    No Known Activations