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

    Neuronpedia

    INDEX
    Explanations

    Spanish language

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the name “Jair Bolsonaro.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     LOC
    -0.07
    .XR
    -0.06
     Whitney
    -0.06
    country
    -0.06
     scour
    -0.06
    eldig
    -0.06
    matched
    -0.06
    _tr
    -0.06
     tầng
    -0.06
    exp
    -0.06
    POSITIVE LOGITS
     lyon
    0.07
    eneration
    0.07
    横
    0.06
    \:
    0.06
    .tail
    0.06
    covers
    0.06
     JAXB
    0.06
    lobe
    0.06
     classes
    0.06
    _IS
    0.06
    Act Density 0.015%

    No Known Activations