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

    Neuronpedia

    INDEX
    Explanations

    news and politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.52
     sánh
    0.49
    ộng
    0.45
     Tanger
    0.45
    <unused2019>
    0.44
     Excel
    0.44
    Universe
    0.44
    anesha
    0.44
    yay
    0.43
    zinger
    0.43
    POSITIVE LOGITS
     denunci
    0.60
     motorists
    0.59
     polizia
    0.56
     policiais
    0.56
     police
    0.54
     ಪೊಲೀ
    0.54
     news
    0.53
    ও
    0.53
     politics
    0.52
     froide
    0.52
    Act Density 0.022%

    No Known Activations