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

    Neuronpedia

    INDEX
    Explanations

    Holocaust history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     creamy
    -0.10
     poke
    -0.09
     Cupertino
    -0.09
     budget
    -0.09
     lateral
    -0.08
     fractional
    -0.08
     paperwork
    -0.08
     smoothie
    -0.08
     procedure
    -0.08
     sement
    -0.07
    POSITIVE LOGITS
     WWII
    0.20
     Holocaust
    0.20
     atrocities
    0.18
     Auschwitz
    0.17
     Nazi
    0.17
     Nazis
    0.16
     Hitler
    0.15
     الحرب
    0.15
     genoc
    0.15
    战争
    0.14
    Act Density 0.113%

    No Known Activations