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

    Neuronpedia

    INDEX
    Explanations

    Entre

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filament
    -0.08
     CONST
    -0.07
    Room
    -0.07
     assessment
    -0.07
    让我
    -0.07
    ومات
    -0.06
     cultivation
    -0.06
     کو
    -0.06
    matches
    -0.06
    _MANAGER
    -0.06
    POSITIVE LOGITS
    .unregister
    0.07
     Entre
    0.06
    alborg
    0.06
    (username
    0.06
     】
    0.06
     İzmir
    0.06
     NavLink
    0.06
    UiThread
    0.06
     dvěma
    0.06
    /?
    0.06
    Act Density 0.003%

    No Known Activations