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

    Neuronpedia

    INDEX
    Explanations

    T5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Spr
    0.42
     fibrils
    0.41
    vrdr
    0.40
     irr
    0.40
    victory
    0.38
     Bluff
    0.36
    iré
    0.36
    Victory
    0.36
     cooper
    0.35
     ойнотуу
    0.35
    POSITIVE LOGITS
     T
    0.46
     الت
    0.44
    IO
    0.42
    IVA
    0.39
    iata
    0.38
    rel
    0.38
    ือบ
    0.37
    댈
    0.37
    Tera
    0.36
    iteta
    0.36
    Act Density 0.007%

    No Known Activations