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

    Neuronpedia

    INDEX
    Explanations

    research on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Iterations
    0.31
    ROUTES
    0.30
    ್ರ
    0.29
     INITIAL
    0.29
    ஜா
    0.28
     complicada
    0.28
     tgt
    0.28
    方案
    0.28
     ies
    0.28
     लेटेस्ट
    0.28
    POSITIVE LOGITS
     repellent
    0.31
     extinguished
    0.29
     repel
    0.28
     snorkel
    0.28
     severe
    0.27
    த்தூர்
    0.27
     plumes
    0.27
     enhanced
    0.27
     invalid
    0.27
     arises
    0.27
    Act Density 0.005%

    No Known Activations