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

    Neuronpedia

    INDEX
    Explanations

    topic sentence and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UX
    0.48
    Software
    0.45
     GitLab
    0.44
     Software
    0.44
    ML
    0.42
     demo
    0.42
     MX
    0.42
     Hardware
    0.41
    MODE
    0.41
    MX
    0.41
    POSITIVE LOGITS
    britann
    0.42
     explanations
    0.41
     Гос
    0.41
     препара
    0.40
    旨在
    0.40
     medications
    0.39
     democracia
    0.39
     incarceration
    0.39
     createFile
    0.39
    遭受
    0.39
    Act Density 0.000%

    No Known Activations