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
    Us
    -0.07
    .*)
    -0.07
     Styles
    -0.06
    (cc
    -0.06
    28
    -0.06
    ,f
    -0.06
     heavier
    -0.06
    око
    -0.06
    ologic
    -0.06
     Hew
    -0.06
    POSITIVE LOGITS
    '];↵
    0.07
     الل
    0.07
    :");↵↵
    0.07
     AIM
    0.06
    ğını
    0.06
    "/>
↵
    0.06
    ằng
    0.06
    !");↵
    0.06
    огу
    0.06
    brain
    0.06
    Act Density 0.210%

    No Known Activations