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

    Neuronpedia

    INDEX
    Explanations

    business reports, regional specialties, specific ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wymien
    0.40
     irritating
    0.38
    Indexs
    0.38
     spanned
    0.38
    बीन
    0.38
     irritate
    0.38
     інших
    0.37
     Eastern
    0.36
     mogą
    0.36
     divertido
    0.36
    POSITIVE LOGITS
    juč
    0.40
    arde
    0.39
     Failing
    0.39
     Sidi
    0.39
     veo
    0.38
    isely
    0.38
    érez
    0.38
    romax
    0.38
     steeds
    0.37
     Glor
    0.37
    Act Density 0.001%

    No Known Activations