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

    Neuronpedia

    INDEX
    Explanations

    App

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    porte
    -0.07
    올
    -0.07
     한번
    -0.07
     Teknik
    -0.06
    ication
    -0.06
     proble
    -0.06
     xe
    -0.06
     twig
    -0.06
     آنها
    -0.06
    LoginForm
    -0.06
    POSITIVE LOGITS
     strangely
    0.06
    ?v
    0.06
    _SY
    0.06
    _define
    0.06
    qrst
    0.06
    Chicken
    0.06
    _GC
    0.06
    _event
    0.06
     جلس
    0.06
     newsletters
    0.06
    Act Density 0.004%

    No Known Activations