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

    Neuronpedia

    INDEX
    Explanations

    nature of subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Com
    0.47
    More
    0.47
    Whatever
    0.46
    Remember
    0.45
    Always
    0.45
    Both
    0.45
    And
    0.44
     Already
    0.44
    Already
    0.44
    Everything
    0.44
    POSITIVE LOGITS
     significance
    1.03
     importance
    0.95
     characteristics
    0.91
     nature
    0.89
     types
    0.82
     meaning
    0.81
     relationship
    0.80
     origins
    0.79
     intricacies
    0.78
     implications
    0.78
    Act Density 0.846%

    No Known Activations