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

    Neuronpedia

    INDEX
    Explanations

    social media platforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rimidine
    0.91
     LMFBR
    0.88
     pathological
    0.74
    odeficiency
    0.73
     विकिरण
    0.73
     reconst
    0.71
     reconstruction
    0.71
    radiation
    0.70
    opharmaceutical
    0.70
     Pto
    0.70
    POSITIVE LOGITS
     Instagram
    3.43
    Instagram
    3.15
     instagram
    2.95
     hashtags
    2.93
     TikTok
    2.92
     Twitter
    2.82
     hashtag
    2.70
    TikTok
    2.63
     Facebook
    2.62
     tiktok
    2.56
    Act Density 1.748%

    No Known Activations