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

    Neuronpedia

    INDEX
    Explanations

    word endings/suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ADHD
    0.75
     IoT
    0.74
     chaos
    0.73
     GDPR
    0.73
     LSTM
    0.70
     YAML
    0.70
     Azure
    0.70
     AI
    0.70
     standard
    0.69
     behavior
    0.69
    POSITIVE LOGITS
    s
    1.57
    e
    1.49
    tidak
    1.42
    t
    1.34
    eine
    1.33
    sning
    1.30
    tle
    1.29
    ecek
    1.28
    sang
    1.28
    ে
    1.27
    Act Density 0.154%

    No Known Activations