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

    Neuronpedia

    INDEX
    Explanations

    proof of delivery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plástico
    0.41
    Após
    0.39
     применяется
    0.38
    ésar
    0.37
     Antennes
    0.37
    UEZ
    0.37
    搀
    0.37
    ច្
    0.36
    🠀
    0.36
    ხვ
    0.35
    POSITIVE LOGITS
     min
    0.39
     deg
    0.38
     Lingu
    0.37
    min
    0.37
     ultimate
    0.37
     unrivalled
    0.36
     Pand
    0.36
    iapkan
    0.36
     irrevocable
    0.35
    暇
    0.35
    Act Density 0.000%

    No Known Activations