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

    Neuronpedia

    INDEX
    Explanations

    consumer electronics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polyvinyl
    0.60
     Escherichia
    0.56
    มนเชสเตอร์
    0.55
     Hewlett
    0.55
     sogenannten
    0.55
     sogenannte
    0.52
     Jawaharlal
    0.51
    中华人民共和国
    0.51
    ⛎
    0.50
     ultraviolet
    0.50
    POSITIVE LOGITS
     соц
    0.71
     devs
    0.70
     GDPR
    0.59
     merch
    0.56
     Rockies
    0.56
     regs
    0.52
     Dems
    0.50
     undergrad
    0.50
     mags
    0.50
     HQ
    0.49
    Act Density 0.032%

    No Known Activations