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

    Neuronpedia

    INDEX
    Explanations

    terms related to criminal activities and laws

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

    Following the word "criminal"

    np_acts-logits-general · gemini-2.0-flash

    crime and criminal context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SpringBootTest
    -0.82
     AssemblyCulture
    -0.78
    parsedMessage
    -0.73
     wünscht
    -0.71
    ValueStyle
    -0.69
    ILayout
    -0.67
     للاسماء
    -0.67
    mybatisplus
    -0.65
    Còn
    -0.64
    הערות
    -0.64
    POSITIVE LOGITS
     crime
    1.32
     crimes
    1.22
     Crime
    1.20
     criminal
    1.08
    Crime
    1.08
     CRIME
    1.04
     Crimin
    1.04
     criminals
    0.98
     Crimes
    0.98
    crime
    0.98
    Act Density 0.274%

    No Known Activations