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

    Neuronpedia

    INDEX
    Explanations

    attacks and violence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     физи
    -0.08
    imestep
    -0.08
    [mem
    -0.08
     slightly
    -0.07
     плот
    -0.07
    pari
    -0.07
     légèrement
    -0.07
    itate
    -0.07
     cumbersome
    -0.07
     Boolean
    -0.07
    POSITIVE LOGITS
     perpetr
    0.11
     occurred
    0.11
     ocurrido
    0.10
     произош
    0.10
     vandal
    0.09
     violence
    0.09
    袭
    0.09
     devastating
    0.09
     murders
    0.09
     धम
    0.09
    Act Density 0.088%

    No Known Activations