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

    Neuronpedia

    INDEX
    Explanations

    before you worry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ناقابل
    0.38
    ˒
    0.38
    傣
    0.38
    Remain
    0.37
     ဆို
    0.36
     Pltf
    0.36
    erek
    0.36
    тература
    0.36
    임을
    0.36
    тения
    0.35
    POSITIVE LOGITS
     worry
    2.45
     worrying
    2.28
     Worry
    2.14
     worried
    2.05
     preocup
    2.05
     worries
    1.92
     걱
    1.70
    担心
    1.66
     preocupa
    1.63
    Wor
    1.59
    Act Density 0.020%

    No Known Activations