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

    Neuronpedia

    INDEX
    Explanations

    saying or expressing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     관련된
    0.82
     సంబంధించిన
    0.68
     aandacht
    0.66
     herhangi
    0.64
     focusing
    0.63
     مرتبط
    0.63
     delves
    0.62
    istin
    0.62
     важли
    0.62
    Exploring
    0.61
    POSITIVE LOGITS
     saying
    3.29
     said
    3.19
     says
    3.12
     say
    2.95
    said
    2.79
    say
    2.70
    says
    2.69
     Says
    2.62
    说
    2.61
    Say
    2.56
    Act Density 0.283%

    No Known Activations