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

    Neuronpedia

    INDEX
    Explanations

    dimensions and physical structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     delusional
    0.45
     virulent
    0.43
     totalitarian
    0.42
     misog
    0.41
     ಭಯ
    0.40
     pretrial
    0.39
     outraged
    0.39
     persecuted
    0.39
     materialistic
    0.39
     disillusioned
    0.39
    POSITIVE LOGITS
     wall
    0.52
     overhang
    0.49
     shelves
    0.49
     recessed
    0.48
     space
    0.47
     corner
    0.45
    Space
    0.45
     Storage
    0.45
     floor
    0.44
     Height
    0.44
    Act Density 0.144%

    No Known Activations