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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    discussions around self-determination and separatist sentiments.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron selectively activates on the token “United” (as in “United States,” “United Kingdom,” “United Nations,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    imony
    -0.07
    _remove
    -0.07
     Negative
    -0.07
    amine
    -0.06
     uno
    -0.06
    ichen
    -0.06
    结果
    -0.06
    anal
    -0.06
    rolled
    -0.06
    -fe
    -0.06
    POSITIVE LOGITS
     وب
    0.07
    (distance
    0.06
    =W
    0.06
     obstruct
    0.06
    �
    0.06
    ुछ
    0.06
    Aws
    0.06
    �
    0.06
    velope
    0.06
     есте
    0.06
    Act Density 0.028%

    No Known Activations