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

    Neuronpedia

    INDEX
    Explanations

    standards and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     weekly
    0.46
     bailout
    0.45
    鈁
    0.45
    теле
    0.45
     mortgage
    0.44
     supermarket
    0.43
     reforma
    0.43
     बीमा
    0.42
     hospital
    0.42
     eurozone
    0.42
    POSITIVE LOGITS
    หรือ
    0.44
     أو
    0.43
    または
    0.42
     ataupun
    0.42
     または
    0.42
     tertentu
    0.41
    或
    0.40
    又は
    0.39
     oder
    0.39
     bestimmten
    0.39
    Act Density 0.001%

    No Known Activations