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
    ian
    -0.08
    IAN
    -0.07
    (cal
    -0.07
    ávka
    -0.07
    ladığı
    -0.07
    Ê
    -0.06
    (ins
    -0.06
    .ot
    -0.06
     models
    -0.06
     tělo
    -0.06
    POSITIVE LOGITS
     Lesb
    0.07
    .ColumnName
    0.06
     بسبب
    0.06
    	↵	↵↵
    0.06
    	Copyright
    0.06
     червня
    0.06
    ूब
    0.06
    ，小
    0.06
    正确
    0.06
     آغاز
    0.06
    Act Density 0.004%

    No Known Activations