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

    Neuronpedia

    INDEX
    Explanations

    object and objectification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    0.77
     ἐ
    0.73
    aders
    0.68
     な
    0.67
    OP
    0.61
     όχι
    0.61
    ുപത്രി
    0.61
     باشد
    0.60
     і
    0.60
    ATES
    0.58
    POSITIVE LOGITS
     Object
    1.15
     object
    1.05
     objek
    1.03
     objects
    0.95
    object
    0.93
     Objekt
    0.92
     objs
    0.89
    t
    0.89
     Objects
    0.88
     OBJ
    0.87
    Act Density 0.066%

    No Known Activations