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

    Neuronpedia

    INDEX
    Explanations

    terminology and concepts related to terrorism and extremist groups

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

    terrorism and goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irited
    -0.47
     migrantes
    -0.47
    autoreleasepool
    -0.46
    IntoConstraints
    -0.45
    lusconi
    -0.40
    ArgsConstructor
    -0.40
    textAppearance
    -0.39
     AssemblyCulture
    -0.39
     migrants
    -0.39
     fiesta
    -0.39
    POSITIVE LOGITS
    ValueStyle
    0.60
     terrorism
    0.52
     terrorist
    0.49
     terrorists
    0.48
    terrorism
    0.48
     терро
    0.45
    terror
    0.45
     Terrorism
    0.44
    ovací
    0.41
    TagMode
    0.38
    Act Density 0.251%

    No Known Activations