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

    Neuronpedia

    INDEX
    Explanations

    dress respectfully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Props
    0.65
     Trial
    0.65
    Ret
    0.63
     Dog
    0.62
    )}$
    0.62
    Mock
    0.61
     re
    0.60
    Clouds
    0.60
    "}
    0.60
     ROC
    0.60
    POSITIVE LOGITS
     havoc
    0.70
     medically
    0.68
     efficiencies
    0.66
    isin
    0.65
     生産
    0.64
    льної
    0.64
    oxone
    0.63
     needs
    0.63
     trinity
    0.63
     partenariat
    0.63
    Act Density 0.000%

    No Known Activations