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

    Neuronpedia

    INDEX
    Explanations

    negative states and nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াগ
    0.46
    Archae
    0.45
    瑪
    0.45
     Archaeology
    0.44
    ла
    0.44
    acijos
    0.44
     bd
    0.44
     Черка
    0.44
    wym
    0.44
     HOLD
    0.44
    POSITIVE LOGITS
     ތ
    0.49
    SearchView
    0.47
     تھی۔
    0.47
    ,/
    0.46
     दावा
    0.44
    /#
    0.44
     Sergeant
    0.44
     ज
    0.43
    PV
    0.43
    ၡ
    0.42
    Act Density 0.000%

    No Known Activations