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
    替
    -0.06
    -graph
    -0.06
     Barry
    -0.06
     insists
    -0.06
     migrant
    -0.06
    _buff
    -0.06
    跨
    -0.06
     بأ
    -0.06
     Dig
    -0.06
     aim
    -0.06
    POSITIVE LOGITS
    product
    0.07
     Oval
    0.07
     horrend
    0.07
    飯店
    0.07
    ▍
    0.07
    'nda
    0.07
     ":"
    0.06
    ευση
    0.06
     offending
    0.06
    .tpl
    0.06
    Act Density 0.113%

    No Known Activations