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

    Neuronpedia

    INDEX
    Explanations

    violence and assault

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filtering
    -0.09
    Filtering
    -0.09
     leak
    -0.09
     Loader
    -0.08
    uart
    -0.08
     Filtering
    -0.08
     substitution
    -0.08
    漏
    -0.08
    .loader
    -0.08
     DVR
    -0.08
    POSITIVE LOGITS
     violence
    0.12
     bruis
    0.12
     assault
    0.10
     injuries
    0.10
     violently
    0.10
     fists
    0.10
     körper
    0.10
     brutality
    0.10
     violent
    0.09
     inflicted
    0.09
    Act Density 0.047%

    No Known Activations