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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     predefined
    -0.06
    \Auth
    -0.06
    اها
    -0.06
     komm
    -0.06
     нашей
    -0.06
    荐
    -0.06
     seine
    -0.06
     Sele
    -0.06
     Paging
    -0.06
    /cm
    -0.06
    POSITIVE LOGITS
     pb
    0.07
     مرتب
    0.06
    .replaceAll
    0.06
    átis
    0.06
    sharp
    0.06
     FAG
    0.06
    _cast
    0.06
    fetchAll
    0.06
     Corp
    0.06
    :self
    0.06
    Act Density 0.006%

    No Known Activations