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

    Neuronpedia

    INDEX
    Explanations

    42

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сен
    -0.08
    :'',↵
    -0.07
    ್ಪ
    -0.07
     intuitive
    -0.07
     relazione
    -0.07
     Kalau
    -0.07
    ijų
    -0.07
     olisi
    -0.07
     plantar
    -0.07
     ജീവന
    -0.07
    POSITIVE LOGITS
    Margins
    0.08
     полов
    0.08
     historically
    0.07
    oli
    0.07
     اسلام
    0.07
     telev
    0.07
     commercials
    0.07
     wides
    0.07
     ±
    0.07
     Москва
    0.07
    Act Density 0.005%

    No Known Activations