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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Present
    -0.08
    Fail
    -0.07
     frantic
    -0.07
    іл
    -0.07
     multin
    -0.07
     сайті
    -0.07
    _web
    -0.07
     projections
    -0.06
     facilitate
    -0.06
    벤
    -0.06
    POSITIVE LOGITS
    اقتص
    0.06
     longing
    0.06
    _quotes
    0.06
    rescia
    0.05
     开
    0.05
    _pressed
    0.05
     secs
    0.05
    (span
    0.05
    �
    0.05
    701
    0.05
    Act Density 0.004%

    No Known Activations