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

    Neuronpedia

    INDEX
    Explanations

    Meta platforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Arduino
    0.69
    ulp
    0.69
     cabling
    0.69
     keV
    0.68
    Terminal
    0.67
     Saxon
    0.67
    DVD
    0.67
     Vag
    0.66
     terminal
    0.66
     Wiring
    0.66
    POSITIVE LOGITS
     Instagram
    2.45
    Instagram
    2.32
     Facebook
    2.30
    Facebook
    2.23
     instagram
    2.08
     TikTok
    2.00
     facebook
    1.89
     इंस्टाग्राम
    1.85
     Zuckerberg
    1.84
    instagram
    1.84
    Act Density 0.604%

    No Known Activations