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

    Neuronpedia

    INDEX
    Explanations

    anxious or stressed states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ის
    0.54
     нарушение
    0.51
    พลาด
    0.49
     RISE
    0.47
    าม
    0.46
     marginalised
    0.46
     obowiąz
    0.46
     rhetoric
    0.45
     ravaged
    0.44
    ayaan
    0.44
    POSITIVE LOGITS
     Vell
    0.49
     exem
    0.48
    巧克力
    0.48
     brokers
    0.44
    z
    0.44
     devise
    0.43
    制造商
    0.41
     Ster
    0.41
     Cookies
    0.40
     Helium
    0.40
    Act Density 0.004%

    No Known Activations