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

    Neuronpedia

    INDEX
    Explanations

    words related to conflict, violence, and social disruption, particularly with named geographic locations.

    oai_token-act-pair · gemini-2.0-flash

    conflict and violence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -1.06
    IntoConstraints
    -0.97
    Geplaatst
    -0.93
     nakalista
    -0.92
    出版年
    -0.91
    DockStyle
    -0.87
     "..\..\..\
    -0.80
     propOrder
    -0.78
     Italijanski
    -0.78
    BagLayout
    -0.77
    POSITIVE LOGITS
     West
    0.40
    cze
    0.40
     Tut
    0.38
     ajutor
    0.37
    West
    0.37
     X
    0.37
    X
    0.37
    endrait
    0.36
    ussch
    0.35
    gegen
    0.35
    Act Density 0.881%

    No Known Activations