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

    Neuronpedia

    INDEX
    Explanations

    English ivy and other plants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Targets
    0.41
     महार
    0.40
     klim
    0.39
     disruption
    0.38
     convolutions
    0.38
     targets
    0.37
     disruptions
    0.37
    బాటు
    0.37
     BL
    0.36
     Prozess
    0.35
    POSITIVE LOGITS
     zmdi
    0.51
    中华人民共和国
    0.45
    ꯡ
    0.42
    红色
    0.39
    abhavam
    0.38
    ά
    0.38
     admon
    0.38
     Необходимо
    0.38
    ἁ
    0.37
     வால்பேப்பர்கள்
    0.37
    Act Density 0.001%

    No Known Activations