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

    Neuronpedia

    INDEX
    Explanations

    my performance evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Petit
    0.54
     Petit
    0.51
    써
    0.45
     petit
    0.42
     quedan
    0.41
     przesz
    0.41
     остаются
    0.40
     queda
    0.39
    াসের
    0.39
    rzez
    0.38
    POSITIVE LOGITS
     Manifest
    0.48
     Measurements
    0.47
     Regions
    0.45
     Acquisitions
    0.45
     Sensors
    0.44
     measurements
    0.42
     Watching
    0.42
     Campaigns
    0.41
     Diagrams
    0.41
     Buds
    0.41
    Act Density 0.001%

    No Known Activations