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

    Neuronpedia

    INDEX
    Explanations

    search query parameters and video identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*.
    0.92
     moves
    0.88
     confusing
    0.88
     /,
    0.87
     /.
    0.87
     moving
    0.86
    /")
    0.84
     confusion
    0.84
     inclusivity
    0.84
     healthcare
    0.84
    POSITIVE LOGITS
    Detail
    1.13
    detail
    1.10
    &=&
    1.05
    ItemID
    1.05
    SearchResult
    1.02
    eyJ
    1.01
    view
    1.01
    search
    1.00
    id
    0.99
    View
    0.96
    Act Density 0.084%

    No Known Activations