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

    Neuronpedia

    INDEX
    Explanations

    review

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of judicial review or appeal proceedings—especially the word “review” and its variants in legal contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gamer
    -0.07
    тож
    -0.07
    URIComponent
    -0.07
    ­های
    -0.06
     slun
    -0.06
     constraint
    -0.06
    ATAR
    -0.06
    policy
    -0.06
     fair
    -0.06
    _tot
    -0.06
    POSITIVE LOGITS
     Audrey
    0.07
    VIS
    0.07
     PHPUnit
    0.07
     giov
    0.06
     Winston
    0.06
     superior
    0.06
     UNSIGNED
    0.06
     reduced
    0.06
    df
    0.06
    ฟ
    0.06
    Act Density 0.003%

    No Known Activations