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

    Neuronpedia

    INDEX
    Explanations

    1900s and 2000s years

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _python
    -0.07
     ecs
    -0.06
    .order
    -0.06
     notch
    -0.06
    HITE
    -0.06
    	Item
    -0.06
    ]+'
    -0.06
    _Admin
    -0.06
    onder
    -0.06
    =N
    -0.06
    POSITIVE LOGITS
    γεν
    0.07
     forums
    0.06
    IEEE
    0.06
    BarController
    0.06
     zag
    0.06
     температуры
    0.06
    .TrimSpace
    0.06
    ampton
    0.06
    祥
    0.06
     socio
    0.06
    Act Density 0.028%

    No Known Activations