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

    Neuronpedia

    INDEX
    Explanations

    related to products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    はこの
    0.43
     инг
    0.41
     weight
    0.40
     integration
    0.39
     annotate
    0.39
    Similarity
    0.37
     аналоги
    0.37
    如果在
    0.37
    可以直接
    0.36
    Якщо
    0.36
    POSITIVE LOGITS
    şti
    0.46
     Trojans
    0.44
    igde
    0.43
    пикир
    0.42
     humiliating
    0.41
    agha
    0.41
    0.41
     cruel
    0.41
     blasp
    0.41
    घात
    0.40
    Act Density 0.000%

    No Known Activations