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

    Neuronpedia

    INDEX
    Explanations

    reset password

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ransport
    0.39
    iau
    0.37
    ahid
    0.37
     Royale
    0.36
     transport
    0.36
     bialgebras
    0.36
     transporte
    0.35
    buje
    0.35
     Transportation
    0.35
     parcel
    0.34
    POSITIVE LOGITS
    ﻨ
    0.43
     Cumber
    0.42
    anam
    0.41
    thanks
    0.41
     ون
    0.40
    时间和
    0.40
     rodzaj
    0.40
     Д
    0.40
    ﻧ
    0.39
     একটু
    0.39
    Act Density 0.001%

    No Known Activations