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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash

    activities related to social justice movements.

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

    The neuron fires on capitalized content words—proper nouns, organizations, movements, and dates—i.e. named‐entity tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ,Y
    -0.07
     unsigned
    -0.07
    <User
    -0.07
     LLP
    -0.06
    (timer
    -0.06
    akah
    -0.06
     squared
    -0.06
     사회
    -0.06
     tuple
    -0.06
     GP
    -0.06
    POSITIVE LOGITS
     McCartney
    0.07
     dout
    0.07
    .'"↵↵
    0.06
     dread
    0.06
     Merrill
    0.06
    ########################################
    0.06
    schema
    0.06
    _gold
    0.05
    _ERROR
    0.05
    ัฒ
    0.05
    Act Density 0.433%

    No Known Activations