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

    Neuronpedia

    INDEX
    Explanations

    multiplicative operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Бу
    0.45
     princípio
    0.38
     Deane
    0.38
    溧
    0.38
     Bene
    0.38
    technik
    0.38
     Sitt
    0.37
    Bene
    0.37
    呸
    0.37
     Геор
    0.37
    POSITIVE LOGITS
     contended
    0.45
     multiplicative
    0.44
     požad
    0.44
     اخبار
    0.42
     multiplying
    0.41
    chunks
    0.41
     سوم
    0.41
     blocs
    0.41
     multiplication
    0.41
     multiplied
    0.40
    Act Density 0.000%

    No Known Activations