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

    Neuronpedia

    INDEX
    Explanations

    world leaders

    np_max-act · gemini-2.0-flash

    This neuron activates on personal names, especially those of prominent political figures and world leaders.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    836
    -0.07
     magazines
    -0.06
     DJ
    -0.06
     archae
    -0.06
    ΙΝ
    -0.06
     Robertson
    -0.06
    /features
    -0.06
    move
    -0.06
    四
    -0.06
     press
    -0.06
    POSITIVE LOGITS
     scares
    0.06
     cookies
    0.06
    _EOL
    0.06
    _SEPARATOR
    0.06
     Nutzung
    0.06
     зобов
    0.06
    pecified
    0.06
    /*.
    0.06
     Blanch
    0.06
     NaN
    0.06
    Act Density 0.025%

    No Known Activations