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

    Neuronpedia

    INDEX
    Explanations

    `form`, `Raw`, `SMA`, `EMA`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     revolution
    0.70
     somente
    0.67
    query
    0.66
     problema
    0.65
     perjud
    0.65
    б
    0.63
     révol
    0.61
    是很
    0.61
    ஹ
    0.60
     resulted
    0.60
    POSITIVE LOGITS
    daki
    0.84
    льное
    0.77
    lera
    0.77
    paces
    0.76
    হেন
    0.76
     Помимо
    0.74
    াক্ত
    0.73
     Elli
    0.73
     slu
    0.73
    leng
    0.73
    Act Density 0.001%

    No Known Activations