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

    Neuronpedia

    INDEX
    Explanations

    listing descriptions for homes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viviendas
    0.52
     apartment
    0.50
     apartments
    0.48
     fuelwood
    0.48
     appartement
    0.46
     boundedness
    0.45
     apartamentos
    0.44
     communal
    0.44
     pertin
    0.44
     formulae
    0.43
    POSITIVE LOGITS
    🎤
    0.43
    คุณ
    0.42
    承認
    0.42
    抖音
    0.42
    กด
    0.41
    TikTok
    0.41
     काउंटर
    0.41
    Porsche
    0.41
     दबा
    0.40
    asko
    0.40
    Act Density 0.001%

    No Known Activations