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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash

    This neuron detects marketing-style superlatives and taglines (e.g. “ultimate hub,” “one-stop shop,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Recruitment
    -0.08
     ма
    -0.06
     Teil
    -0.06
     جزء
    -0.06
    _windows
    -0.06
     Nob
    -0.06
     compensate
    -0.06
     manufact
    -0.06
     magazine
    -0.06
     UIT
    -0.06
    POSITIVE LOGITS
    _locator
    0.07
    ственной
    0.06
    國際
    0.06
    mq
    0.06
    vale
    0.06
    =max
    0.06
    sys
    0.06
    antro
    0.06
    �
    0.06
     disfr
    0.06
    Act Density 0.015%

    No Known Activations