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

    Neuronpedia

    INDEX
    Explanations

    specific entities and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    論文
    0.50
    lectual
    0.43
    Lou
    0.41
    маш
    0.40
    论文
    0.39
    pubmed
    0.39
    Volunteer
    0.38
     अध्यापक
    0.38
     census
    0.37
    femin
    0.37
    POSITIVE LOGITS
    !).
    0.42
     freel
    0.42
     FRE
    0.41
     fre
    0.40
    fre
    0.40
    ))*
    0.38
    Ũ
    0.38
    鍱
    0.37
    !)
    0.36
    !"
    0.36
    Act Density 0.001%

    No Known Activations