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

    Neuronpedia

    INDEX
    Explanations

    800 helpline number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atorii
    0.70
     Caught
    0.64
    出版社
    0.63
    侶
    0.63
    <unused974>
    0.62
    誨
    0.62
     षटके
    0.62
    استشهاد
    0.62
     joueurs
    0.62
     publishers
    0.62
    POSITIVE LOGITS
    вый
    0.68
     long
    0.68
     σει
    0.68
    दी
    0.66
    玻璃
    0.66
    ready
    0.66
    cine
    0.65
     శా
    0.63
    月
    0.63
     मौ
    0.63
    Act Density 0.014%

    No Known Activations