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

    Neuronpedia

    INDEX
    Explanations

    exoneration/innocence

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of legal exoneration or being freed—especially in contexts involving DNA evidence.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ub
    -0.07
    Disc
    -0.06
    ансов
    -0.06
    ichtig
    -0.06
    posite
    -0.06
     Accessories
    -0.06
     Built
    -0.06
    lang
    -0.06
     quot
    -0.06
    lbrace
    -0.06
    POSITIVE LOGITS
    favorite
    0.07
    Smarty
    0.07
     nj
    0.07
     Верхов
    0.06
     fizik
    0.06
    Favorite
    0.06
     státní
    0.06
    ITableView
    0.06
    UMAN
    0.06
     UF
    0.06
    Act Density 0.009%

    No Known Activations