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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with both violent crime and international conflict

    oai_token-act-pair · gemini-2.0-flash

    negative events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brazos
    -0.56
    luci
    -0.52
     semi
    -0.48
     Siegel
    -0.47
    getExternal
    -0.47
     sides
    -0.46
    luis
    -0.46
     Ombudsman
    -0.46
    TRIBUN
    -0.46
    гун
    -0.46
    POSITIVE LOGITS
     cherchés
    0.81
     tartalomajánló
    0.68
    IGraphics
    0.65
    ptonshire
    0.64
    Personendaten
    0.63
    AndEndTag
    0.63
     arşivlendi
    0.63
     propOrder
    0.62
     unsafe
    0.60
    fromnode
    0.60
    Act Density 1.075%

    No Known Activations