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

    Neuronpedia

    INDEX
    Explanations

    men

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on tokens referring to the 1989 Tiananmen Square protests.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     oder
    -0.07
    uses
    -0.07
     BODY
    -0.06
    ictory
    -0.06
     sliding
    -0.06
    Damage
    -0.06
     Tests
    -0.06
     dateString
    -0.06
    ACKET
    -0.06
    ackets
    -0.06
    POSITIVE LOGITS
    。他
    0.07
     здат
    0.06
     interracial
    0.06
     �
    0.06
    .jetbrains
    0.06
    雷
    0.06
     Nikon
    0.06
     Вики
    0.06
    عنوان
    0.06
     Social
    0.06
    Act Density 0.003%

    No Known Activations