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

    Neuronpedia

    INDEX
    Explanations

    parts of descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patronage
    0.51
     Belle
    0.46
     mitigating
    0.46
     autres
    0.46
    ро
    0.46
     patrons
    0.46
     अन्याय
    0.45
     competency
    0.44
     belle
    0.43
     mercenaries
    0.43
    POSITIVE LOGITS
    cB
    0.51
    تل
    0.45
     Steps
    0.43
     लाहि
    0.42
     السما
    0.42
    ted
    0.42
    txt
    0.42
    łącz
    0.42
     تل
    0.41
     ժ
    0.41
    Act Density 0.000%

    No Known Activations