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

    Neuronpedia

    INDEX
    Explanations

    housing and shelter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.54
    动作
    0.50
    ната
    0.49
    見える
    0.48
    elijk
    0.46
    eração
    0.45
     görünt
    0.45
     supérieure
    0.45
     الموجود
    0.45
     blo
    0.44
    POSITIVE LOGITS
    ट
    0.73
     bagi
    0.68
     FOR
    0.64
    แรม
    0.64
    determining
    0.63
     アイス
    0.63
    ﺕ
    0.61
     ส
    0.61
    duire
    0.61
    ль
    0.60
    Act Density 0.026%

    No Known Activations