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

    Neuronpedia

    INDEX
    Explanations

    feeling and looking better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    -2.41
    籏
    -1.74
     reveló
    -1.47
    oluble
    -1.38
    豋
    -1.37
    盉
    -1.36
     benefícios
    -1.34
     lanza
    -1.34
    笵
    -1.33
     soluções
    -1.32
    POSITIVE LOGITS
     what
    1.59
     more
    1.58
     both
    1.55
     not
    1.41
     less
    1.37
     which
    1.36
     better
    1.34
     all
    1.34
     good
    1.33
     with
    1.27
    Act Density 0.021%

    No Known Activations