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

    Neuronpedia

    INDEX
    Explanations

    expenserecorded temperatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.47
    rath
    0.40
     Palisades
    0.40
     Rath
    0.38
     Artes
    0.38
     конце
    0.37
     vertex
    0.37
     herm
    0.37
     Ziel
    0.37
    投げ
    0.36
    POSITIVE LOGITS
    私が
    0.43
    㑓
    0.41
     моей
    0.41
    Nigerian
    0.41
    зья
    0.40
    私は
    0.39
    序列
    0.39
     minha
    0.39
    criar
    0.38
     Items
    0.38
    Act Density 0.000%

    No Known Activations