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

    Neuronpedia

    INDEX
    Explanations

    ...

    np_max-act · gemini-2.0-flash

    The neuron fires on subjective opinion words—especially sentiment-laden adjectives and adverbs expressing praise or criticism.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     एम
    -0.06
     Healthcare
    -0.06
    监督
    -0.06
     tsl
    -0.06
     Zu
    -0.06
    Twig
    -0.06
    502
    -0.06
    700
    -0.06
     Fast
    -0.06
     getUsers
    -0.05
    POSITIVE LOGITS
    .basename
    0.07
    (UIAlertAction
    0.07
     більше
    0.06
     уник
    0.06
    .named
    0.06
    .FindElement
    0.06
     muschi
    0.06
    才能
    0.06
    _strlen
    0.06
    _unlock
    0.06
    Act Density 0.074%

    No Known Activations