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

    Neuronpedia

    INDEX
    Explanations

    Specific terms and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     हड्डियों
    0.39
    κος
    0.39
    োক
    0.38
     मार
    0.37
    কেন
    0.37
    clust
    0.37
    也就是说
    0.37
    ὅ
    0.36
     アンティーク
    0.36
    removeFrom
    0.36
    POSITIVE LOGITS
    ))^
    0.42
    ↵
    0.42
    .
    0.42
     prosa
    0.41
     Experience
    0.39
     Cedex
    0.39
     Merkezi
    0.38
     Languages
    0.38
    ,"
    0.38
    ."
    0.37
    Act Density 0.013%

    No Known Activations