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

    Neuronpedia

    INDEX
    Explanations

    fact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distinctly
    -0.08
     Vice
    -0.08
     пад
    -0.08
     серв
    -0.07
    DROP
    -0.07
     креп
    -0.07
     cramped
    -0.07
     wastes
    -0.07
     Edo
    -0.07
     край
    -0.07
    POSITIVE LOGITS
     determination
    0.08
     ră
    0.08
    専門
    0.07
     araştır
    0.07
     esimerkiksi
    0.07
     searches
    0.07
     termites
    0.07
    ರಾಗ
    0.07
     ruok
    0.07
     opin
    0.07
    Act Density 0.003%

    No Known Activations