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

    Neuronpedia

    INDEX
    Explanations

    connection to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     episcopal
    1.06
     overcame
    1.00
    侗
    1.00
     Ants
    0.98
    ንዳንድ
    0.97
     arenas
    0.95
     APAC
    0.95
    其
    0.95
     wouldn
    0.95
     ADF
    0.95
    POSITIVE LOGITS
    о
    1.43
     dangere
    1.25
     erat
    1.23
    กับการ
    1.23
    at
    1.15
    am
    1.15
    กับ
    1.14
    pm
    1.11
    arra
    1.11
    end
    1.09
    Act Density 0.869%

    No Known Activations