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

    Neuronpedia

    INDEX
    Explanations

    research studies and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sempre
    0.83
     always
    0.79
     siempre
    0.78
     instinctively
    0.74
     chaos
    0.73
     hide
    0.73
     gibt
    0.72
     suave
    0.72
     darkness
    0.72
     spesso
    0.72
    POSITIVE LOGITS
     исследова
    1.21
     исследования
    1.20
     methodological
    1.19
     undertaken
    1.18
     연구
    1.16
     penelitian
    1.16
     questionnaires
    1.14
     questionnaire
    1.11
    Researchers
    1.11
     undertook
    1.11
    Act Density 0.007%

    No Known Activations