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

    Neuronpedia

    INDEX
    Explanations

    close to numbers or percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     únicas
    0.46
     fetus
    0.46
     únicos
    0.44
     médecins
    0.44
     họ
    0.44
     pairings
    0.43
     fatalities
    0.43
     cysts
    0.43
     pragmatic
    0.42
     internship
    0.42
    POSITIVE LOGITS
    the
    0.48
    숫
    0.44
    your
    0.43
    working
    0.43
     hopelessly
    0.42
    Exploring
    0.41
    observation
    0.41
    sidebar
    0.41
    gol
    0.40
    Designing
    0.40
    Act Density 0.003%

    No Known Activations