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

    Neuronpedia

    INDEX
    Explanations

    White House and its associated entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ers
    0.64
    riel
    0.60
    ra
    0.59
    rives
    0.59
    tera
    0.58
    ität
    0.57
     Trichodesmium
    0.57
    る
    0.57
    -【
    0.57
    ro
    0.56
    POSITIVE LOGITS
    ки
    0.71
    ي
    0.70
    。
    0.67
    ک
    0.65
    ين
    0.64
    не
    0.63
    फ़
    0.61
     app
    0.60
    ف
    0.59
    ﮑ
    0.59
    Act Density 0.002%

    No Known Activations