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

    Neuronpedia

    INDEX
    Explanations

    writing options or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     volcanoes
    0.80
     microorganisms
    0.79
     halides
    0.73
     spacecraft
    0.73
     impover
    0.71
     organisms
    0.70
     biosynthesis
    0.69
     centuries
    0.69
     microbes
    0.69
     inhomogeneities
    0.69
    POSITIVE LOGITS
    ควร
    0.79
    should
    0.76
    追加
    0.72
    Should
    0.72
    应
    0.71
     Should
    0.66
    committee
    0.65
    chedule
    0.65
     should
    0.64
     هذا
    0.64
    Act Density 0.001%

    No Known Activations