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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     budget
    -0.07
    _CARD
    -0.06
     medication
    -0.06
     anybody
    -0.06
     объект
    -0.06
     deeds
    -0.06
     irritation
    -0.06
    .fill
    -0.06
    InvalidArgumentException
    -0.06
     umbrella
    -0.06
    POSITIVE LOGITS
     ук
    0.07
     lø
    0.07
    .tel
    0.06
     enamel
    0.06
    .ipv
    0.06
    صف
    0.06
    ्पन
    0.06
    ่อง
    0.06
     #-}↵
    0.06
    -utils
    0.06
    Act Density 0.394%

    No Known Activations