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

    Neuronpedia

    INDEX
    Explanations

    definitions or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    solution
    0.45
    дование
    0.45
    Popen
    0.43
    ösungen
    0.43
    শিপ
    0.43
    Й
    0.41
    Д
    0.41
    Σ
    0.41
    Solution
    0.41
    measure
    0.41
    POSITIVE LOGITS
     límite
    0.44
     δεί
    0.44
     enough
    0.43
     October
    0.42
     açık
    0.41
    粝
    0.41
     groupBy
    0.40
     Gorg
    0.40
     contento
    0.40
     nahm
    0.39
    Act Density 0.017%

    No Known Activations