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

    Neuronpedia

    INDEX
    Explanations

    arithmetic contexts and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     corz
    0.44
    苣
    0.41
     subtropical
    0.41
    νοι
    0.40
    釀
    0.40
    ocèle
    0.39
    Glu
    0.39
    лася
    0.39
     méthodique
    0.38
     شرطونه
    0.38
    POSITIVE LOGITS
     Mr
    0.37
     Toyota
    0.36
    納税
    0.36
    هایت
    0.36
     accuses
    0.36
     TE
    0.35
    住所
    0.35
     ET
    0.35
     genomics
    0.35
     বিবাহ
    0.34
    Act Density 0.003%

    No Known Activations