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

    Neuronpedia

    INDEX
    Explanations

    non-english characters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lineup
    0.37
     muzzle
    0.36
     클
    0.36
    큼
    0.36
     ROD
    0.35
     wur
    0.35
     xgb
    0.35
     óleo
    0.35
     lên
    0.34
     čo
    0.34
    POSITIVE LOGITS
    天空
    0.37
    जेदार
    0.35
    較
    0.34
     никаких
    0.34
     குறி
    0.34
     চেষ্ট
    0.34
     வேறு
    0.33
     checklists
    0.33
    வச
    0.33
    帰
    0.32
    Act Density 0.001%

    No Known Activations