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

    Neuronpedia

    INDEX
    Explanations

    Lorem ipsum Sed do eiusmod

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Od
    0.39
    coco
    0.39
    od
    0.39
    ehl
    0.36
     Od
    0.35
    鹄
    0.35
    elfde
    0.35
     চির
    0.34
     McGuire
    0.34
    취
    0.34
    POSITIVE LOGITS
     тип
    0.46
     conferences
    0.42
     vacanam
    0.40
     writer
    0.39
     rhythm
    0.38
    ẩu
    0.38
     Extras
    0.37
    тип
    0.37
    結
    0.37
     sm
    0.37
    Act Density 0.001%

    No Known Activations