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

    Neuronpedia

    INDEX
    Explanations

    learning software features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     malware
    -0.07
     famine
    -0.07
    Solo
    -0.07
    (graph
    -0.07
     tablet
    -0.06
     نتایج
    -0.06
    Su
    -0.06
    \Query
    -0.06
     Tud
    -0.06
     drama
    -0.06
    POSITIVE LOGITS
    鎮
    0.07
     захворю
    0.07
     heure
    0.06
    통령
    0.06
     MAKE
    0.06
    іблі
    0.06
    �
    0.06
    /weather
    0.06
     biased
    0.06
     NFL
    0.06
    Act Density 0.133%

    No Known Activations