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

    Neuronpedia

    INDEX
    Explanations

    python function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いた
    0.77
    age
    0.75
    {
    0.73
     l
    0.71
    ↵↵
    0.70
    it
    0.66
     "
    0.61
     internas
    0.61
    ot
    0.60
     St
    0.60
    POSITIVE LOGITS
    0.71
    duino
    0.69
    ер
    0.68
    lığı
    0.68
    lığ
    0.68
    IMENTO
    0.67
    дох
    0.66
    ER
    0.65
    dcsset
    0.65
    CEPTION
    0.64
    Act Density 0.263%

    No Known Activations