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

    Neuronpedia

    INDEX
    Explanations

    multiplication expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Be
    0.78
    be
    0.70
    লেও
    0.66
    Custom
    0.62
     लापता
    0.61
    ωσε
    0.60
    އް
    0.59
    etc
    0.59
    testng
    0.59
    和其他
    0.58
    POSITIVE LOGITS
     ×
    2.65
    ×
    2.28
     multiplied
    2.15
    >×</
    1.97
     multiply
    1.87
    1.83
    乘以
    1.79
    ϫ
    1.73
     คูณ
    1.73
     multiplying
    1.73
    Act Density 0.287%

    No Known Activations