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

    Neuronpedia

    INDEX
    Explanations

    based

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ర్లు
    0.42
    にとって
    0.38
    કામાં
    0.37
    γγελμα
    0.36
     کردیا
    0.36
    သို့
    0.34
    प्लेस
    0.34
    యన
    0.33
    ermanfaat
    0.33
    क्रोश
    0.33
    POSITIVE LOGITS
     based
    4.19
     Based
    3.77
     BASED
    3.63
    Based
    3.61
    based
    3.52
     berdasarkan
    3.36
     basado
    3.30
    基于
    3.28
     dựa
    3.27
     basada
    3.17
    Act Density 0.563%

    No Known Activations