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

    Neuronpedia

    INDEX
    Explanations

    mathematical representation and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oxidase
    0.43
    MakeRect
    0.42
     ligands
    0.41
     lingers
    0.41
    hamilan
    0.41
    wiches
    0.40
    heta
    0.40
    េច
    0.40
     왼
    0.40
     waitress
    0.39
    POSITIVE LOGITS
     Further
    0.53
     Re
    0.41
    进一步
    0.41
     Fatima
    0.41
     further
    0.41
     HashMap
    0.40
     ESP
    0.40
     Be
    0.39
     Reduced
    0.39
     Embed
    0.38
    Act Density 0.000%

    No Known Activations