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

    Neuronpedia

    INDEX
    Explanations

    assumes or believing followed by determiner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    感受到
    0.77
    inqui
    0.77
    Bias
    0.73
     clearly
    0.72
     unsettled
    0.70
     disappointment
    0.70
     unsett
    0.70
     ใจ
    0.70
     scepticism
    0.70
     जल्द
    0.69
    POSITIVE LOGITS
    ına
    0.77
    i
    0.68
    いる
    0.66
    ÿ
    0.66
     Pem
    0.66
    ay
    0.64
     provenant
    0.64
    e
    0.64
    aing
    0.63
     włas
    0.62
    Act Density 0.245%

    No Known Activations