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

    Neuronpedia

    INDEX
    Explanations

    little followed by adjectives/adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    2.95
     gesamten
    2.69
     comboBox
    2.65
    бычно
    2.55
     aikana
    2.46
     cuales
    2.46
     excelentes
    2.44
    ब
    2.41
    際は
    2.39
     unul
    2.39
    POSITIVE LOGITS
     leeway
    3.07
     dozen
    2.64
    씩
    2.45
    dozen
    2.45
    খানি
    2.44
    વાર
    2.41
    మంది
    2.35
    ν
    2.32
    чис
    2.29
    儿
    2.23
    Act Density 0.196%

    No Known Activations