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

    Neuronpedia

    INDEX
    Explanations

    .google

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of “google” in domain names or URLs (e.g., “maps.google.com,” “drive.google.com,” “translate.google.com”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Basel
    -0.07
    FFT
    -0.06
    くる
    -0.06
    Digits
    -0.06
    ,!
    -0.06
    COM
    -0.06
     زم
    -0.06
     Rao
    -0.06
    лиж
    -0.06
     حذف
    -0.06
    POSITIVE LOGITS
     attendees
    0.07
    'name
    0.07
    inline
    0.07
     �
    0.07
    super
    0.07
     runner
    0.07
     inputData
    0.06
     fost
    0.06
    @g
    0.06
     nIndex
    0.06
    Act Density 0.003%

    No Known Activations