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

    Neuronpedia

    INDEX
    Explanations

    sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    546
    -0.06
    _Login
    -0.06
    Presenter
    -0.06
    subscriptions
    -0.06
     "#{
    -0.06
     слу
    -0.06
    correct
    -0.06
    Password
    -0.06
     final
    -0.06
    rectangle
    -0.06
    POSITIVE LOGITS
     Adjustment
    0.08
    !*
    0.06
     oluyor
    0.06
     Sb
    0.06
     ci
    0.06
    ivial
    0.06
     mol
    0.06
    von
    0.06
    _Bar
    0.06
     دستی
    0.06
    Act Density 0.015%

    No Known Activations