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

    Neuronpedia

    INDEX
    Explanations

    death and loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     답
    -0.08
    -----------
    -0.08
     တ
    -0.08
     loja
    -0.08
     contienen
    -0.08
     문자열
    -0.08
    .preprocessing
    -0.08
    -response
    -0.08
    Sb
    -0.08
    .fit
    -0.07
    POSITIVE LOGITS
     tragic
    0.17
     tragedies
    0.17
     victims
    0.15
     tragedy
    0.15
     deaths
    0.15
     casualties
    0.14
     fatalities
    0.14
     heartbreaking
    0.14
     décès
    0.13
    Deaths
    0.13
    Act Density 0.136%

    No Known Activations