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

    Neuronpedia

    INDEX
    Explanations

    social media content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fred
    -0.08
     SOUND
    -0.08
    brates
    -0.08
     정신
    -0.08
     proté
    -0.08
     électron
    -0.08
     métall
    -0.08
     diab
    -0.08
    ophobia
    -0.08
     ion
    -0.08
    POSITIVE LOGITS
    Instagram
    0.19
     hashtags
    0.19
     Instagram
    0.18
     सोशल
    0.18
    微博
    0.17
     hashtag
    0.17
    .instagram
    0.16
     ट्विटर
    0.16
     સોશિયલ
    0.16
     instagram
    0.16
    Act Density 0.276%

    No Known Activations