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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal proceedings, such as arrests, charges, and sentences

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

    Legal consequences: arrested, prosecuted, or imprisoned

    np_acts-logits-general · gemini-2.0-flash

    legal consequences and reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.89
     '\\;'
    -0.84
    WithIOException
    -0.84
     חיצוניים
    -0.78
     متعلقه
    -0.77
     للمعارف
    -0.75
    DockStyle
    -0.75
    出版年
    -0.73
     esternos
    -0.71
     Meksiku
    -0.69
    POSITIVE LOGITS
     kerana
    0.79
     vì
    0.76
     because
    0.73
     karena
    0.70
     over
    0.65
     based
    0.64
     wegen
    0.61
     accused
    0.60
     atas
    0.59
     بسبب
    0.58
    Act Density 0.376%

    No Known Activations