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

    Neuronpedia

    INDEX
    Explanations

    numbers and financial terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ikat
    0.42
    ulet
    0.39
     defining
    0.38
    సిన
    0.38
    itektur
    0.38
    itent
    0.38
    ডো
    0.38
    ough
    0.37
     Jackman
    0.36
    ucc
    0.36
    POSITIVE LOGITS
     blancs
    0.40
     modifica
    0.37
     بالأ
    0.37
    INE
    0.36
     disputes
    0.36
     bialgebras
    0.36
     führen
    0.36
     supre
    0.36
     پک
    0.36
     семина
    0.36
    Act Density 0.000%

    No Known Activations