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

    Neuronpedia

    INDEX
    Explanations

    System; namespace declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mitigate
    0.54
    ко
    0.46
     tinnitus
    0.46
    <unused1861>
    0.46
     ისინი
    0.45
     diarrhea
    0.44
    <unused364>
    0.44
     tóc
    0.43
     shutout
    0.43
    പ്പെടുത്ത
    0.42
    POSITIVE LOGITS
    ਮ
    0.52
     ehemal
    0.47
     entsprechenden
    0.46
    の上
    0.46
    avoir
    0.45
     Ünivers
    0.45
    my
    0.44
     meinen
    0.44
     Giải
    0.43
     Universitas
    0.42
    Act Density 0.001%

    No Known Activations