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

    Neuronpedia

    INDEX
    Explanations

    containment or enclosure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    attham
    0.47
    Subsection
    0.42
    listItem
    0.41
    OpenJDK
    0.41
    ड्यू
    0.40
    劻
    0.40
    Delay
    0.39
    टावा
    0.39
    immediately
    0.39
     immediately
    0.38
    POSITIVE LOGITS
     catholic
    0.43
     ern
    0.42
     culprits
    0.41
     species
    0.40
     Kos
    0.40
     m
    0.40
     Catholic
    0.39
    vij
    0.39
     Vogel
    0.38
     ros
    0.38
    Act Density 0.000%

    No Known Activations