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

    Neuronpedia

    INDEX
    Explanations

    formatting and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     아니
    0.39
     ਇੱਕ
    0.38
     പോലുള്ള
    0.37
     decirlo
    0.37
    Cela
    0.36
     tandis
    0.35
     împre
    0.35
    𝐨
    0.35
    纶
    0.35
     शब्दा
    0.34
    POSITIVE LOGITS
     for
    0.44
     refineries
    0.40
    包括
    0.40
     refinery
    0.39
     to
    0.39
     ports
    0.39
     propane
    0.38
     (
    0.38
     from
    0.38
    for
    0.38
    Act Density 0.121%

    No Known Activations