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

    Neuronpedia

    INDEX
    Explanations

    follow up questions or resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nya
    1.19
    ted
    0.93
    ians
    0.90
    et
    0.90
    र्ज
    0.90
    chen
    0.90
    lated
    0.88
    swith
    0.86
    ton
    0.83
    esis
    0.83
    POSITIVE LOGITS
     permittivity
    0.93
     Почему
    0.90
     demikian
    0.89
    াকর
    0.88
     marshmallow
    0.84
     SizedBox
    0.84
     Så
    0.84
    }{\
    0.81
     complementarity
    0.81
     zarządz
    0.80
    Act Density 0.035%

    No Known Activations