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

    Neuronpedia

    INDEX
    Explanations

    lists of abstract descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Antibodies
    0.87
     Magazines
    0.86
     Diagnosis
    0.82
    लेट्स
    0.81
     tornadoes
    0.80
     herbicides
    0.80
     hexagons
    0.80
     वेव्स
    0.79
     iPads
    0.79
     GPUs
    0.79
    POSITIVE LOGITS
     managerial
    0.94
     organizational
    0.90
     psychological
    0.89
     behavioral
    0.89
    otional
    0.86
     sociological
    0.85
     technological
    0.85
     philosophical
    0.84
    ological
    0.84
     structural
    0.84
    Act Density 0.240%

    No Known Activations