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

    Neuronpedia

    INDEX
    Explanations

    advertising agency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这两个
    0.86
     estas
    0.85
     이렇게
    0.80
     această
    0.80
    未使用
    0.78
    dimensions
    0.77
     данной
    0.77
    CLEAR
    0.77
     논
    0.77
     በዚህ
    0.77
    POSITIVE LOGITS
    atcher
    0.72
     '.'
    0.70
    ever
    0.69
    '=>
    0.67
     tuo
    0.65
     communicating
    0.64
     vốn
    0.62
    もので
    0.62
     '
    0.61
    ifying
    0.61
    Act Density 0.000%

    No Known Activations