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

    Neuronpedia

    INDEX
    Explanations

    conditional situations

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect references to drugs (e.g. mentions of “drogas”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    624
    -0.07
    29
    -0.07
    037
    -0.07
     sands
    -0.06
     gode
    -0.06
     Trap
    -0.06
     extensions
    -0.06
     Forbidden
    -0.06
    Trading
    -0.06
     önc
    -0.06
    POSITIVE LOGITS
    (interval
    0.07
     suyu
    0.06
    ferred
    0.06
    �인
    0.06
    urg
    0.06
    antom
    0.06
     swiper
    0.06
     زیرا
    0.06
    غط
    0.06
     {};↵↵
    0.06
    Act Density 0.053%

    No Known Activations