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

    Neuronpedia

    INDEX
    Explanations

    Political activism/protests

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “Charlie Hebdo,” i.e. references to the Charlie Hebdo attack.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ≡≡
    -0.07
     nói
    -0.07
    _Group
    -0.07
    _APPEND
    -0.06
    ...↵↵↵
    -0.06
    责
    -0.06
     heir
    -0.06
    GetSize
    -0.06
    ález
    -0.06
    -chain
    -0.06
    POSITIVE LOGITS
     pray
    0.07
    .Cache
    0.07
     Science
    0.07
    íc
    0.06
     kli
    0.06
    ائر
    0.06
     science
    0.06
    frei
    0.06
    210
    0.06
    汉
    0.06
    Act Density 0.002%

    No Known Activations