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

    Neuronpedia

    INDEX
    Explanations

    linear regression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    viewer
    0.46
    ವಹ
    0.41
     gelin
    0.41
     viewers
    0.40
     viewer
    0.39
    視聴
    0.38
    receptor
    0.37
    kts
    0.37
    ალური
    0.36
    त्रियों
    0.36
    POSITIVE LOGITS
     espress
    0.46
     Twitter
    0.45
     Scott
    0.45
    (((
    0.44
     Discord
    0.44
     Anth
    0.43
     Instagram
    0.42
     Edgar
    0.42
     Nose
    0.42
    bae
    0.41
    Act Density 0.000%

    No Known Activations