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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arbitrary
    -0.06
    _renderer
    -0.06
     parameters
    -0.06
     relationships
    -0.06
     Noon
    -0.06
    چ
    -0.06
    Custom
    -0.06
    <
    -0.06
    .Client
    -0.06
     secondary
    -0.05
    POSITIVE LOGITS
    .GetMapping
    0.07
     sexist
    0.07
    iyorlar
    0.07
    (intent
    0.06
     københavn
    0.06
     pornofilm
    0.06
     planta
    0.06
     sklad
    0.06
     smr
    0.06
     �
    0.06
    Act Density 0.023%

    No Known Activations