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

    Neuronpedia

    INDEX
    Explanations

    would have children

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    玛
    0.52
    ্তার
    0.45
     शिवा
    0.44
    0.43
    ┎
    0.43
    িল
    0.43
    貉
    0.42
    瑪
    0.41
    曼
    0.40
     판매
    0.40
    POSITIVE LOGITS
     in
    0.44
     singularities
    0.44
     copious
    0.44
     $=
    0.44
     specifying
    0.43
     involves
    0.42
     elucidated
    0.42
    ;"
    0.40
     including
    0.40
    ῖς
    0.40
    Act Density 0.005%

    No Known Activations