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

    Neuronpedia

    INDEX
    Explanations

    social media platforms and profiles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᅵ
    0.40
    頪
    0.38
    ในสนาม
    0.37
    SOFTWARE
    0.36
    nih
    0.36
    wc
    0.35
    udders
    0.35
    lyn
    0.35
    亍
    0.35
    getClass
    0.34
    POSITIVE LOGITS
     platform
    0.66
    上で
    0.64
    上的
    0.61
    平台
    0.61
     plataforma
    0.59
     hesab
    0.54
     searches
    0.54
     Marketplace
    0.54
     users
    0.53
     profiles
    0.53
    Act Density 0.047%

    No Known Activations