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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron flags references to geographic locations—especially the phrase “the city of …” and similar place‐name mentions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     '**
    -0.07
    apper
    -0.07
     Operational
    -0.07
     Separator
    -0.07
     Thế
    -0.07
     포함
    -0.06
     مخصوص
    -0.06
    te
    -0.06
    pot
    -0.06
     RaisePropertyChanged
    -0.06
    POSITIVE LOGITS
    NSBundle
    0.06
    Κ
    0.06
    芝
    0.06
     JB
    0.06
    ]];↵
    0.06
     flaws
    0.06
     jour
    0.05
     dětí
    0.05
    --;
↵
    0.05
     dịch
    0.05
    Act Density 0.008%

    No Known Activations