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

    Neuronpedia

    INDEX
    Explanations

    at least or its core

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loob
    0.29
     dä
    0.26
     miejsce
    0.25
    Includes
    0.25
    Possibly
    0.25
     Possibly
    0.24
    Included
    0.24
    Nombre
    0.24
     intensifying
    0.23
     Fragments
    0.23
    POSITIVE LOGITS
     حداقل
    0.31
     least
    0.29
    least
    0.26
    至少
    0.26
    طلا
    0.26
    少なくとも
    0.26
     جیسا
    0.25
     Least
    0.23
    ⑴
    0.23
     秋
    0.23
    Act Density 0.027%

    No Known Activations