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

    Neuronpedia

    INDEX
    Explanations

    object relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     finans
    0.84
    妻
    0.78
    ுற
    0.75
     قوان
    0.73
     سفر
    0.71
     financi
    0.70
    軼
    0.70
     సినిమా
    0.69
    idez
    0.68
     ખાતે
    0.68
    POSITIVE LOGITS
     object
    5.58
     objects
    5.43
    object
    5.19
     Objects
    4.98
     Object
    4.90
    objects
    4.85
    Object
    4.84
     objeto
    4.60
    Objects
    4.58
     objetos
    4.49
    Act Density 0.754%

    No Known Activations