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

    Neuronpedia

    INDEX
    Explanations

    list items, including

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ordinairement
    0.53
     varient
    0.52
     generalmente
    0.50
     kebanyakan
    0.48
     biraz
    0.48
     geralmente
    0.48
     normalerweise
    0.48
     genellikle
    0.48
     whitish
    0.47
     naturels
    0.46
    POSITIVE LOGITS
    including
    0.61
    包括
    0.55
     including
    0.54
     Including
    0.54
    includes
    0.53
     включая
    0.52
     včetně
    0.52
     Includes
    0.51
     includes
    0.51
    provide
    0.50
    Act Density 0.124%

    No Known Activations