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

    Neuronpedia

    INDEX
    Explanations

    even just by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Viruses
    0.44
    ι
    0.42
    I
    0.42
    ரிக்கை
    0.42
     کل
    0.41
    สาร
    0.41
     Örneğin
    0.41
     Vertrag
    0.40
     நாடுகளில்
    0.40
    𝐼
    0.40
    POSITIVE LOGITS
    診断
    0.44
     techn
    0.43
     unapolog
    0.42
    hosting
    0.42
     králov
    0.42
     véritable
    0.41
    ᄈ
    0.41
     scouting
    0.40
     punishable
    0.40
     //'
    0.40
    Act Density 0.004%

    No Known Activations