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

    Neuronpedia

    INDEX
    Explanations

    Key

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mandato
    0.52
    Mam
    0.50
     malu
    0.48
    Fitting
    0.48
     Mam
    0.48
     malo
    0.48
     සං
    0.48
    হাওয়া
    0.48
    挠
    0.47
     grief
    0.47
    POSITIVE LOGITS
     improvements
    0.65
     Improvements
    0.64
    improvements
    0.63
     improvement
    0.57
     Verbesser
    0.54
    Improvements
    0.54
    Improve
    0.54
    改善
    0.50
    improvement
    0.50
     Improvement
    0.49
    Act Density 0.070%

    No Known Activations